Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8371
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlEnum
    -0.50
     bestaande
    -0.37
     parç
    -0.37
     comerciais
    -0.36
     combinar
    -0.35
     sztu
    -0.35
     væ
    -0.34
     Behaup
    -0.34
     embaraz
    -0.34
     Bedürfn
    -0.34
    POSITIVE LOGITS
     officer
    3.66
     officers
    3.56
     Officers
    3.45
     Officer
    3.44
    officer
    3.34
    Officer
    3.34
    officers
    3.28
    Officers
    3.25
     OFFICER
    3.16
     OFFICERS
    2.97
    Activations Density 0.084%

    No Known Activations