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. 23-GEMMASCOPE-RES-16K
    6. 7595
    Prev
    Next
    INDEX
    Explanations

    data types and related constructs in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newBuilder
    -0.60
    disposing
    -0.58
    matchCondition
    -0.55
    ReferenceEquals
    -0.53
    encodeWith
    -0.53
     ब्रेकडाउन
    -0.53
     Signalez
    -0.52
    uxxxx
    -0.52
     pä
    -0.52
     AssemblyProduct
    -0.52
    POSITIVE LOGITS
    ?=
    0.70
    AutoScaleMode
    0.64
    .*")]
    0.60
    ública
    0.57
    ?
    0.54
     =
    0.52
     AssemblyCulture
    0.51
    prefixer
    0.50
    ئيس
    0.49
    IntoConstraints
    0.49
    Activations Density 0.110%

    No Known Activations