© 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. 46988
    Prev
    Next
    INDEX
    Explanations

    special characters and technical formatting in data or code

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

    jpg, vary, strip

    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
    GeneratedCode
    -0.52
     '\\;'
    -0.46
     Cerebral
    -0.45
    LEncoder
    -0.44
     CURIAM
    -0.44
     Bridget
    -0.43
    OGND
    -0.43
    GeoNames
    -0.42
    sunt
    -0.42
    MainThread
    -0.41
    POSITIVE LOGITS
    inary
    0.62
    INARY
    0.45
     upload
    0.40
     argint
    0.40
     photoshoot
    0.40
     tazas
    0.38
     noDo
    0.36
     lác
    0.34
     verw
    0.34
     uploaded
    0.34
    Activations Density 0.000%

    No Known Activations