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. 33-GEMMASCOPE-RES-16K
    6. 11567
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with regulation, legal actions, and illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arqu
    -0.39
    dafx
    -0.39
     AttributeSet
    -0.39
     disappointments
    -0.39
     predictable
    -0.37
     merve
    -0.37
    áját
    -0.37
     vời
    -0.36
     változ
    -0.36
     سرد
    -0.36
    POSITIVE LOGITS
     illegal
    2.47
     illegally
    2.25
    illegal
    2.13
     Illegal
    1.94
    Illegal
    1.91
     unlawful
    1.88
     ilegal
    1.88
     illicit
    1.88
     illeg
    1.72
     unlawfully
    1.66
    Activations Density 0.959%

    No Known Activations