© 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. 4-GEMMASCOPE-RES-16K
    11. 1739
    Prev
    Next
    INDEX
    Explanations

    instances of police-related actions and terms associated with stopping and detaining individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hintergrund
    -0.55
     linkovi
    -0.53
    disposing
    -0.53
     Prensa
    -0.49
     achtergrond
    -0.48
     semantics
    -0.48
    agrad
    -0.47
    پیوند
    -0.47
    RESUMO
    -0.46
    Diss
    -0.46
    POSITIVE LOGITS
     stopped
    1.23
     Stopping
    1.17
     stopping
    1.15
     Stopped
    1.13
     stops
    1.13
    Stopping
    1.12
     stop
    1.08
     stopp
    1.04
     Stops
    1.04
    stopping
    1.03
    Activations Density 0.327%

    No Known Activations