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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 53885
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions, organizations, and their roles in research or healthcare contexts

    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
    IntoConstraints
    -0.38
     University
    -0.35
    netje
    -0.35
    ⤹
    -0.33
    ŚCI
    -0.32
     Sul
    -0.32
     Lon
    -0.32
     bu
    -0.32
     übers
    -0.31
     single
    -0.31
    POSITIVE LOGITS
    VersionUID
    0.66
    webElementXpaths
    0.60
    ":[{
    0.57
     defaultstate
    0.56
     bParam
    0.54
    DIPSETTING
    0.52
    IsMutable
    0.51
    cookieParser
    0.51
     betweenstory
    0.50
     RemoteException
    0.50
    Activations Density 0.101%

    No Known Activations