© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 15936
    Prev
    Next
    INDEX
    Explanations

    references to users

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zdan
    -0.68
     apper
    -0.68
    anskje
    -0.66
     digress
    -0.66
     /\.(
    -0.63
     despatch
    -0.62
     quenching
    -0.59
    annica
    -0.59
    invent
    -0.59
     combineReducers
    -0.59
    POSITIVE LOGITS
    user
    2.36
     user
    2.00
     User
    1.73
    User
    1.70
    USER
    1.60
     USER
    1.50
    用户
    1.06
     IUser
    1.02
    GetUser
    0.97
     GetUser
    0.97
    Activations Density 0.049%

    No Known Activations