© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 17590
    Prev
    Next
    INDEX
    Explanations

    references to regulations and regulatory processes

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

    regulation and governance

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    MessageOf
    -0.53
    DoubleQuotes
    -0.48
    EndContext
    -0.43
    delwed
    -0.43
    ⤒
    -0.41
    GEBURTS
    -0.40
    LookAnd
    -0.40
    ElementException
    -0.39
     utafitiHapana
    -0.39
    IndexPath
    -0.38
    POSITIVE LOGITS
     regulation
    1.36
     REGULATION
    1.20
     Regulation
    1.19
    regulation
    1.19
     regulatory
    1.15
     regulate
    1.12
    Regulation
    1.12
     regulación
    1.11
     regulated
    1.09
     regulations
    1.05
    Activations Density 0.028%

    No Known Activations