© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 77921
    Prev
    Next
    INDEX
    Explanations

    terms related to legal compliance and regulations

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

    applicable law

    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
    Autoritní
    -0.59
    Pautan
    -0.57
    TagMode
    -0.55
     Италијани
    -0.51
    исленность
    -0.48
    üyor
    -0.47
    ########.
    -0.47
    LookAnd
    -0.47
    UrlResolution
    -0.46
    TypedDataSet
    -0.46
    POSITIVE LOGITS
     applicable
    2.02
    applicable
    1.70
     APPLICABLE
    1.52
    Applicable
    1.50
     Applicable
    1.49
     aplicable
    1.37
     relevant
    1.06
     appropriate
    1.05
     pertinent
    0.98
     inapplicable
    0.93
    Activations Density 0.003%

    No Known Activations