© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7808
    Prev
    Next
    INDEX
    Explanations

    features related to compactness and portability in electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to product features describing compactness, lightweight, and portability in technical descriptions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    descriptions emphasizing portability and space efficiency—items being small, lightweight, thin, and designed to fold, stow, or otherwise minimize storage.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical descriptions of physical products emphasizing compact size, portability, and space-saving features.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionMode
    -0.40
     rospy
    -0.36
    ABULARY
    -0.36
    UnusedPrivate
    -0.35
    Business
    -0.35
    RTSC
    -0.34
     HFILL
    -0.34
    Rcpp
    -0.34
    dott
    -0.34
    Референце
    -0.33
    POSITIVE LOGITS
     compact
    0.72
     compactness
    0.65
    コンパクト
    0.64
     collapsible
    0.62
     компакт
    0.60
    compact
    0.60
     folded
    0.60
     compacto
    0.59
     Compact
    0.58
     intptr
    0.58
    Activations Density 0.090%

    No Known Activations