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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 7592
    Prev
    Next
    INDEX
    Explanations

    occurrences of blank spaces or indentation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coper
    -0.49
     ActivatedRoute
    -0.48
    statusText
    -0.47
     The
    -0.46
     كه
    -0.45
     ◄
    -0.44
    ~,
    -0.43
     bu
    -0.43
     Tradu
    -0.43
     Bu
    -0.42
    POSITIVE LOGITS
    NameInMap
    1.00
    MigrationBuilder
    0.83
     protoimpl
    0.79
    ThroughAttribute
    0.78
    tagHelperRunner
    0.77
    RenderAtEndOf
    0.76
     GeoNames
    0.74
    LookAnd
    0.73
     "..\..\..\
    0.73
     @"/
    0.72
    Activations Density 0.016%

    No Known Activations