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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 163
    Prev
    Next
    INDEX
    Explanations

    references to users and their interactions with systems or interfaces

    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
     FetchType
    -0.71
     AutoMapper
    -0.66
    TypedDataSet
    -0.62
     AppModule
    -0.61
    offsetof
    -0.61
    }$​
    -0.60
     NIP
    -0.58
    DockStyle
    -0.58
     AppComponent
    -0.58
    AnimationsModule
    -0.57
    POSITIVE LOGITS
     user
    2.29
     users
    2.13
     Users
    1.90
     User
    1.90
    Users
    1.65
     USER
    1.56
     utilisateur
    1.55
    user
    1.53
     gebruikers
    1.50
    users
    1.49
    Activations Density 0.080%

    No Known Activations