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. 3-GEMMASCOPE-RES-16K
    6. 12704
    Prev
    Next
    INDEX
    Explanations

    specific pronouns and phrases related to the speaker's personal experience and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSprite
    -0.82
    minton
    -0.66
    InjectAttribute
    -0.62
     AssemblyCulture
    -0.62
     transfieras
    -0.59
     Serap
    -0.59
    XtraGrid
    -0.59
    then
    -0.57
    艋
    -0.57
     propOrder
    -0.57
    POSITIVE LOGITS
    opter
    0.56
    UnknownFields
    0.56
     فريبيس
    0.54
    esez
    0.49
     StatelessWidget
    0.47
     onCancelled
    0.46
     كمان
    0.43
     zuk
    0.43
    ゅう
    0.43
    Dos
    0.42
    Activations Density 0.151%

    No Known Activations