© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5136
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory compliance and safety regarding substance usage and monitoring

    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
    yntax
    -0.45
    úgó
    -0.43
    givings
    -0.38
    itinéraire
    -0.37
    ItemIndex
    -0.36
    ➟
    -0.35
    ゴリ
    -0.35
    ンダント
    -0.35
    +#+#
    -0.34
    yntaxException
    -0.34
    POSITIVE LOGITS
     access
    0.48
    Tikang
    0.48
     Accessible
    0.47
     فريبيس
    0.46
    antMatchers
    0.46
     Access
    0.45
    )_/¯
    0.45
     restriction
    0.44
    UnsafeEnabled
    0.44
    access
    0.44
    Activations Density 0.876%

    No Known Activations