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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9862
    Prev
    Next
    INDEX
    Explanations

    technical terms and structured data related to programming and data management

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

    HTML table, class, or template-related code

    np_acts-logits-general · gemini-2.0-flash

    code and technical language

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Италијани
    -0.74
     الرياضيه
    -0.69
    Rujuakan
    -0.68
    migrationBuilder
    -0.68
    featureID
    -0.67
    Geplaatst
    -0.65
     Meksiku
    -0.65
    دانشنامهٔ
    -0.64
     ویکی‌پدی
    -0.63
     Infórmanos
    -0.63
    POSITIVE LOGITS
     ho
    0.36
     uLocal
    0.32
    pumpe
    0.31
     уровня
    0.30
     charité
    0.30
    オフ
    0.28
    zio
    0.28
     Opfer
    0.28
    MAK
    0.27
     asociado
    0.27
    Activations Density 1.013%

    No Known Activations