© 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. 12-GEMMASCOPE-RES-16K
    11. 5830
    Prev
    Next
    INDEX
    Explanations

    mentions of arrests or legal actions involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     firebaseConfig
    -0.45
    complexContent
    -0.41
    arakhand
    -0.39
     incentive
    -0.36
     Loire
    -0.36
    ARAN
    -0.36
     ARIA
    -0.35
    Espan
    -0.35
    illoma
    -0.35
     pandangan
    -0.35
    POSITIVE LOGITS
     Arrest
    1.16
     arrest
    1.15
    Arrest
    1.12
     arrests
    1.09
    arrest
    1.07
     arrested
    1.03
     Arrested
    0.89
     arresting
    0.82
     detención
    0.79
    逮捕
    0.77
    Activations Density 0.444%

    No Known Activations