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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4807
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebControls
    -0.60
    Portály
    -0.56
    GEBURTSDATUM
    -0.55
    quirer
    -0.53
     attendu
    -0.52
    </tfoot>
    -0.52
    DoubleQuotes
    -0.51
    IndentedString
    -0.50
    ález
    -0.48
    ministrazione
    -0.48
    POSITIVE LOGITS
     therefrom
    0.63
    सन्दर्भ
    0.60
     thereof
    0.59
     ervan
    0.54
    bitField
    0.52
     therein
    0.52
    GOTREF
    0.49
    aclk
    0.48
    requestCode
    0.48
     therewith
    0.47
    Activations Density 0.728%

    No Known Activations