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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3181
    Prev
    Next
    INDEX
    Explanations

    terms and phrases relating to compliance and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adhering to rules or standards

    np_acts-logits-general · gemini-2.0-flash

    compliance with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.61
    LookAnd
    -0.59
    Parcelize
    -0.54
     resourceCulture
    -0.53
    
    -0.51
    Dtor
    -0.50
     Carn
    -0.50
    SBATCH
    -0.49
     castor
    -0.49
    styleType
    -0.49
    POSITIVE LOGITS
     compliance
    1.88
     Compliance
    1.77
    Compliance
    1.69
    compliance
    1.66
     comply
    1.38
     compliant
    1.29
     complies
    1.27
     complying
    1.27
    PLIANCE
    1.27
    compliant
    1.25
    Activations Density 0.280%

    No Known Activations