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. 13-GEMMASCOPE-RES-16K
    6. 13843
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical problem-solving and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.53
    NewUrlParser
    -0.47
     investment
    -0.47
    addGroup
    -0.47
    BeginContext
    -0.45
    lineTo
    -0.44
     contribution
    -0.42
     yyj
    -0.42
     eux
    -0.42
    dding
    -0.42
    POSITIVE LOGITS
    FilterChain
    0.81
    StoreMessageInfo
    0.68
     przeprowad
    0.67
    UserScript
    0.67
    ecuzione
    0.66
     execute
    0.66
     Numerade
    0.66
     Durchführung
    0.65
    فيذ
    0.65
    execSQL
    0.64
    Activations Density 0.656%

    No Known Activations