Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 95203
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to server configuration and operations

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

    server configuration paths

    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
     సౌకర్య
    -0.41
     تضيفلها
    -0.39
     plegable
    -0.39
    ్రామ
    -0.37
     meninos
    -0.37
    felizmente
    -0.37
     iniciado
    -0.36
     RouterModule
    -0.36
     barrera
    -0.35
    GeoNames
    -0.35
    POSITIVE LOGITS
    EndContext
    0.70
     للمعارف
    0.69
     ivelany
    0.66
    Personensuche
    0.54
    MessageOf
    0.53
    хьтан
    0.52
    DockStyle
    0.51
    ErrUnexpectedEOF
    0.50
    tagHelperRunner
    0.50
    ChildScrollView
    0.49
    Activations Density 0.017%

    No Known Activations