© 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. 21-GEMMASCOPE-RES-16K
    11. 8993
    Prev
    Next
    INDEX
    Explanations

    phrases related to user interaction and experience with systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.70
    ScopeManager
    -0.62
    QMetaType
    -0.59
    PullParser
    -0.56
    GIVEREF
    -0.53
    URLConnection
    -0.53
     مُعرِّف
    -0.51
    ftagPool
    -0.51
     refreshToken
    -0.51
     AspNetCore
    -0.50
    POSITIVE LOGITS
     users
    2.36
     user
    2.13
     end
    1.95
     Users
    1.94
    Users
    1.79
    users
    1.78
    user
    1.70
    用户
    1.66
     USERS
    1.66
     utilisateurs
    1.62
    Activations Density 0.454%

    No Known Activations