© 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. 25-GEMMASCOPE-RES-16K
    11. 15450
    Prev
    Next
    INDEX
    Explanations

    terms related to justifications and rulings in criminal cases involving shootings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.46
     projects
    -0.43
     nahilalakip
    -0.43
    嬉しいです
    -0.41
     Neuer
    -0.40
     regions
    -0.40
    AndEndTag
    -0.40
     Chwiliwch
    -0.40
     success
    -0.39
     portfolios
    -0.39
    POSITIVE LOGITS
    Investigators
    0.75
     investigation
    0.75
    Investigation
    0.72
     investigators
    0.72
    investigation
    0.67
    Investigations
    0.65
     investigating
    0.61
     INVESTIGATION
    0.60
    investig
    0.60
     investigations
    0.60
    Activations Density 1.029%

    No Known Activations