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. 75263
    Prev
    Next
    INDEX
    Explanations

    function calls and variable assignments related to session management in code

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

    key, name, and configuration parameters

    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
     ves
    -0.39
    CloseOperation
    -0.38
    ثيق
    -0.37
     htmlFor
    -0.37
     video
    -0.36
    isSuccessful
    -0.36
     fakta
    -0.35
     Escor
    -0.35
     VizieR
    -0.34
     roleId
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.62
    findpost
    0.51
    RetentionPolicy
    0.51
    Notae
    0.49
     anuales
    0.48
     barbati
    0.45
    arakhand
    0.44
     pères
    0.43
    Diwedd
    0.42
     Reſ
    0.42
    Activations Density 0.004%

    No Known Activations