© 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. 11-GEMMASCOPE-RES-16K
    11. 5383
    Prev
    Next
    INDEX
    Explanations

    terms related to regulation and regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     köpek
    -0.45
    Compound
    -0.43
    Persona
    -0.42
     Whitehead
    -0.42
     compound
    -0.42
    ObjectID
    -0.41
    Hai
    -0.41
    FirstName
    -0.41
    Child
    -0.41
     Compound
    -0.40
    POSITIVE LOGITS
     regulation
    1.51
     regulated
    1.42
     regulate
    1.41
     REGULATION
    1.41
    regulation
    1.40
     Regulation
    1.38
     REGUL
    1.34
     regulating
    1.33
     Regulated
    1.32
    Regulation
    1.29
    Activations Density 0.261%

    No Known Activations