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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8659
    Prev
    Next
    INDEX
    Explanations

    specific commands and structures related to database creation and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    حياتها
    -0.53
    حياته
    -0.48
    Rüyada
    -0.35
    trad
    -0.35
    ThemeOverlay
    -0.34
    gridad
    -0.33
     continuidad
    -0.33
    🔕
    -0.33
    
    -0.33
     demanded
    -0.33
    POSITIVE LOGITS
    UserScript
    0.60
     pleaſure
    0.55
    ніципалі
    0.53
    原始内容存档
    0.47
     uſe
    0.47
    aarrggbb
    0.46
    BagLayout
    0.45
     ſol
    0.45
     ſche
    0.45
    Race
    0.44
    Activations Density 0.236%

    No Known Activations