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. 20-GEMMASCOPE-RES-131K
    6. 90068
    Prev
    Next
    INDEX
    Explanations

    mentions of static elements or references in programming and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    rungsseite
    -0.76
    ChildScrollView
    -0.71
     GoogleFonts
    -0.68
    setVerticalGroup
    -0.66
     snippetHide
    -0.66
    windowFixed
    -0.66
    featureID
    -0.65
     himo
    -0.64
    VYMaps
    -0.63
    libft
    -0.61
    POSITIVE LOGITS
     hur
    0.28
     collective
    0.28
     collectively
    0.28
     assisted
    0.27
     kvar
    0.26
     Dorsey
    0.26
    verhältnisse
    0.26
     popular
    0.26
    没人
    0.26
     voci
    0.26
    Activations Density 0.178%

    No Known Activations