© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12717
    Prev
    Next
    INDEX
    Explanations

    instances of arrests and related legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     înc
    -0.39
    Portail
    -0.35
     pokrač
    -0.34
    phosa
    -0.34
     Aussch
    -0.32
     motive
    -0.32
    illoma
    -0.31
    willReturn
    -0.31
     fan
    -0.30
     décrire
    -0.30
    POSITIVE LOGITS
     arrest
    1.36
     arrested
    1.34
    arrest
    1.32
    Arrest
    1.32
     Arrest
    1.31
     arrests
    1.30
     Arrested
    1.11
     arresting
    1.09
    逮捕
    0.93
     detención
    0.82
    Activations Density 0.345%

    No Known Activations