Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6621
    Prev
    Next
    INDEX
    Explanations

    quoted strings and punctuated expressions within a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.72
    "
    -0.72
     Hartman
    -0.72
    ",
    -0.63
    Harbor
    -0.62
     Harbor
    -0.62
    ”
    -0.62
    anan
    -0.61
    aura
    -0.60
    chili
    -0.60
    POSITIVE LOGITS
    sweise
    0.55
     ''){
    0.49
     Turquía
    0.48
     Meksika
    0.47
    Oleh
    0.47
     colectiva
    0.46
    řeba
    0.46
    erdings
    0.46
     Tipp
    0.45
     británico
    0.44
    Activations Density 0.221%

    No Known Activations