© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7655
    Prev
    Next
    INDEX
    Explanations

    information related to various fields, particularly electronics, education, and sports

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

    words related to technical or academic fields such as electronics, theater, education, and genetics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    CloseOperation
    -0.66
     ligiloj
    -0.58
    LLocation
    -0.57
    يميديا
    -0.54
    awtextra
    -0.52
    BagConstraints
    -0.50
    rungsseite
    -0.50
    oa̍t
    -0.48
    Ārējās
    -0.47
     otomatig
    -0.46
    POSITIVE LOGITS
     оригіналу
    0.48
    audiovisuel
    0.41
     equivalently
    0.40
    ンダー
    0.39
    󠁴
    0.37
    collant
    0.36
    rodek
    0.36
    openqa
    0.36
    labelControl
    0.35
    튀
    0.35
    Activations Density 0.670%

    No Known Activations