© 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. 31-GEMMASCOPE-RES-131K
    6. 21165
    Prev
    Next
    INDEX
    Explanations

    terms related to complex biological and evolutionary concepts or conditions

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

    qualities of phenomena and features

    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
    parsedMessage
    -0.71
     pinulongan
    -0.66
     ainfi
    -0.59
    :✨
    -0.55
     defaultstate
    -0.54
     myſelf
    -0.52
    CloseOperation
    -0.50
    ंदीखरीदारी
    -0.48
     desmotivaciones
    -0.48
    */),
    -0.48
    POSITIVE LOGITS
     feature
    0.94
     thing
    0.85
     phenomenon
    0.85
     aspect
    0.84
     requirement
    0.83
     issue
    0.81
     attribute
    0.80
     tactic
    0.80
     option
    0.79
     element
    0.79
    Activations Density 0.122%

    No Known Activations