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. 19-GEMMASCOPE-RES-16K
    6. 15612
    Prev
    Next
    INDEX
    Explanations

    references to statistics and figures related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vats
    -0.44
    ibly
    -0.43
     American
    -0.42
     ricordi
    -0.41
    suff
    -0.41
    ải
    -0.41
    ậy
    -0.40
     nguy
    -0.40
     cả
    -0.40
    otri
    -0.40
    POSITIVE LOGITS
     autorytatywna
    1.03
     ProtoMessage
    0.97
     EconPapers
    0.97
    MigrationBuilder
    0.89
     فريبيس
    0.85
    NameInMap
    0.79
     HasFactory
    0.79
     للمعارف
    0.77
     Chwiliwch
    0.77
     ligiloj
    0.75
    Activations Density 0.521%

    No Known Activations