© 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. 772
    Prev
    Next
    INDEX
    Explanations

    programming elements related to code structure and definitions

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

    technical source code and configuration details, particularly programming-related syntax and file paths.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     isInitialized
    -0.55
     betweenstory
    -0.51
     مشين
    -0.51
     كومونز
    -0.47
    pulumi
    -0.41
    ambién
    -0.40
     CURIAM
    -0.39
    awtextra
    -0.38
    QMetaType
    -0.37
    thenReturn
    -0.37
    POSITIVE LOGITS
     위해
    0.50
     Partridge
    0.48
     Verwendung
    0.47
     */,
    0.47
     Geschä
    0.46
     besar
    0.46
     Hidalgo
    0.46
    ⓘ
    0.46
     Lernen
    0.46
     aikaa
    0.46
    Activations Density 0.884%

    No Known Activations