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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 805
    Prev
    Next
    INDEX
    Explanations

    function and method declarations in code snippets

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.64
     Chwiliwch
    -0.64
    EDEFAULT
    -0.63
    TintMode
    -0.61
    帖最后由
    -0.60
    Читати
    -0.57
    GEBURTSDATUM
    -0.56
     незавершена
    -0.55
    styleType
    -0.54
    EndGlobal
    -0.54
    POSITIVE LOGITS
     TestBed
    0.44
     bienvenida
    0.39
     sek
    0.35
    BASEPATH
    0.35
    AndroidJUnit
    0.35
     hembra
    0.34
    emplo
    0.33
     Región
    0.32
    setContentView
    0.30
     governed
    0.30
    Activations Density 0.009%

    No Known Activations