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. 25-GEMMASCOPE-RES-16K
    6. 1885
    Prev
    Next
    INDEX
    Explanations

    organizations and their associated functions or components within a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fossa
    -0.58
    amitié
    -0.49
    ższe
    -0.49
     adult
    -0.49
     camar
    -0.49
    metology
    -0.49
     Strada
    -0.48
    meral
    -0.45
    \}\\
    -0.45
     Amic
    -0.44
    POSITIVE LOGITS
    apache
    0.86
    springframework
    0.75
    slf
    0.73
    openqa
    0.68
    junit
    0.66
    Personendaten
    0.66
    codehaus
    0.65
     mergeFrom
    0.63
    jetbrains
    0.62
     ModelExpression
    0.61
    Activations Density 0.117%

    No Known Activations