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. 38-GEMMASCOPE-RES-16K
    6. 8796
    Prev
    Next
    INDEX
    Explanations

    references to criminal law and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crime
    -0.68
     Crime
    -0.64
    crime
    -0.62
     Crimes
    -0.62
     crimes
    -0.61
     CRIME
    -0.60
     crimen
    -0.57
    Crime
    -0.57
     crimin
    -0.54
     criminal
    -0.53
    POSITIVE LOGITS
    Autoritní
    0.50
     justice
    0.49
    TintMode
    0.48
     transfieras
    0.44
    EDEFAULT
    0.43
    justice
    0.43
     Савезне
    0.40
    ISTICS
    0.40
    PARATUS
    0.39
     JUSTICE
    0.38
    Activations Density 0.408%

    No Known Activations