© 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. 69382
    Prev
    Next
    INDEX
    Explanations

    references to customer service and guarantees

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

    stand behind

    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
     exit
    -1.59
     Exit
    -1.48
    exit
    -1.29
     exits
    -1.27
    Exit
    -1.26
     EXIT
    -1.20
    EXIT
    -1.12
     exiting
    -1.10
     exited
    -1.05
    exits
    -0.92
    POSITIVE LOGITS
     stands
    0.73
     stand
    0.73
     Stand
    0.71
    Stand
    0.70
    stand
    0.68
     stood
    0.67
    stands
    0.66
     STAND
    0.66
    STAND
    0.63
    Standing
    0.63
    Activations Density 0.040%

    No Known Activations