© 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. 10-GEMMASCOPE-RES-16K
    11. 13519
    Prev
    Next
    INDEX
    Explanations

    terms related to legal arrests and custody

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bitField
    -0.75
    doo
    -0.71
    psack
    -0.68
    PrivateRoute
    -0.68
    riezmann
    -0.66
    wdata
    -0.65
     Trip
    -0.65
     Goodwin
    -0.65
    Dirk
    -0.63
    iram
    -0.63
    POSITIVE LOGITS
     arrests
    1.25
     arrest
    1.16
     Arrest
    1.12
    arrest
    1.10
     arrested
    1.09
    Arrest
    1.07
     arresting
    0.92
     Arrested
    0.89
     Majefty
    0.80
     polaire
    0.79
    Activations Density 0.084%

    No Known Activations