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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 61885
    Prev
    Next
    INDEX
    Explanations

    variable terms and indices in mathematical and scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    parameter values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     autorytatywna
    -0.84
    parsedMessage
    -0.78
    AddTagHelper
    -0.77
     Autorizaciones
    -0.74
    rungsseite
    -0.71
     CreateTagHelper
    -0.70
    Legături
    -0.70
    ロウィン
    -0.70
    IsContent
    -0.69
    aarrggbb
    -0.69
    POSITIVE LOGITS
     match
    0.27
    ądź
    0.24
    兵
    0.24
    +:+
    0.23
    <eos>
    0.22
     hinaus
    0.22
     alike
    0.21
     Reise
    0.21
     Match
    0.20
     at
    0.20
    Activations Density 0.166%

    No Known Activations