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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6117
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing quality or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tibus
    -0.34
     Presidencia
    -0.34
    stości
    -0.33
     Fußballspieler
    -0.32
    судар
    -0.30
     redire
    -0.30
    getWindow
    -0.29
    犯
    -0.29
    Discografia
    -0.29
     desejo
    -0.28
    POSITIVE LOGITS
    ThroughAttribute
    0.81
     nice
    0.80
    Nice
    0.77
    脚注の使い方
    0.75
     Nice
    0.75
    excellent
    0.72
    tagHelperRunner
    0.70
    Excelente
    0.69
     wonderful
    0.69
    NICE
    0.68
    Activations Density 0.264%

    No Known Activations