© 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. 31-GEMMASCOPE-RES-131K
    11. 65760
    Prev
    Next
    INDEX
    Explanations

    specific types of businesses and services related to health, recreation, and culture

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

    names, places, or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Einfluß
    -0.56
     Geschäft
    -0.54
     ſind
    -0.52
     maș
    -0.52
     tekem
    -0.52
     vendar
    -0.51
     kysy
    -0.50
     Schluß
    -0.50
    ocarc
    -0.49
    ecuted
    -0.48
    POSITIVE LOGITS
    ↵↵
    0.58
     defaultstate
    0.47
     للاسماء
    0.47
    ):
    0.45
    0.43
    ])):
    0.42
    0.42
    ↵↵↵↵
    0.42
    </h5>
    0.42
    RTSN
    0.42
    Activations Density 0.014%

    No Known Activations