© 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. 9-GEMMASCOPE-RES-131K
    6. 13841
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to variables, positive integers, roots, and inequalities

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

    non-negative and positive numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glVertex
    -0.52
    tagHelperRunner
    -0.47
     للمعارف
    -0.45
    RenderAtEndOf
    -0.43
    市镇
    -0.42
    ″]
    -0.42
     
    -0.40
    ']]
    -0.40
    ')")
    -0.40
    jutnya
    -0.39
    POSITIVE LOGITS
     nonnegative
    0.48
    RUnlock
    0.47
    setVerticalGroup
    0.46
    SerializedSize
    0.45
     positivas
    0.45
     usize
    0.45
     dương
    0.43
     inocente
    0.42
    scry
    0.42
    NSUInteger
    0.41
    Activations Density 0.333%

    No Known Activations