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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 11470
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and syntax elements related to object and data declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handlung
    -0.48
    mique
    -0.47
    gesi
    -0.46
    okko
    -0.45
    esai
    -0.44
    افت
    -0.44
     SURVEY
    -0.44
    gestellt
    -0.44
     SECTOR
    -0.43
    stellungs
    -0.43
    POSITIVE LOGITS
    AT
    0.73
    }{*}{
    0.73
    AS
    0.73
    IS
    0.72
     AS
    0.72
     AN
    0.71
    bParam
    0.70
    AP
    0.70
    AM
    0.69
    setVerticalGroup
    0.69
    Activations Density 0.594%

    No Known Activations