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. 3-GEMMASCOPE-RES-16K
    6. 6404
    Prev
    Next
    INDEX
    Explanations

    references to the Eclipse software or its related components

    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
     AssemblyCulture
    -0.88
    tagHelperRunner
    -0.74
    FormTagHelper
    -0.73
    bootstrapcdn
    -0.72
    GenerationType
    -0.72
    Odkazy
    -0.69
     مشين
    -0.67
    Törté
    -0.67
    brainly
    -0.66
     Scalars
    -0.66
    POSITIVE LOGITS
    Wür
    0.54
     SRS
    0.52
    TID
    0.51
     dresser
    0.48
    etration
    0.48
     eletrônico
    0.47
     Orpheus
    0.47
    gaz
    0.46
    MigrationBuilder
    0.46
     equalization
    0.46
    Activations Density 0.086%

    No Known Activations