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. 122756
    Prev
    Next
    INDEX
    Explanations

    email addresses or mentions of accounts

    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
    saraba
    -0.33
     floor
    -0.33
     QtWidgets
    -0.31
     sir
    -0.30
    ":[{
    -0.30
    ⓧ
    -0.30
     chi
    -0.29
    tonsoft
    -0.29
     JpaRepository
    -0.28
    rspec
    -0.28
    POSITIVE LOGITS
    ariConfig
    0.64
     мәкал
    0.60
     Biôgrafia
    0.60
    ьажоргаш
    0.59
    ValueStyle
    0.58
    RegistryLite
    0.57
    دانشنامهٔ
    0.57
     estekak
    0.57
     conoci
    0.56
     kaarangay
    0.55
    Activations Density 0.000%

    No Known Activations