© 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. 20-GEMMASCOPE-RES-131K
    11. 31711
    Prev
    Next
    INDEX
    Explanations

    instances of the variable 'x' in mathematical expressions or equations

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

    mathematical variables or code 'x'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    debounce
    -0.57
    subpackage
    -0.54
    dette
    -0.54
    Portale
    -0.53
    cloudflare
    -0.53
     Maitland
    -0.53
     صوتيه
    -0.52
     Pelleg
    -0.52
    tenham
    -0.51
     Bernadette
    -0.51
    POSITIVE LOGITS
    x
    1.09
    X
    1.07
     x
    1.02
     X
    0.93
    getX
    0.89
    setX
    0.84
     getX
    0.84
     Xander
    0.71
    xs
    0.69
    xH
    0.67
    Activations Density 0.137%

    No Known Activations