Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67534
    Prev
    Next
    INDEX
    Explanations

    terms related to weight and mass measurements

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

    physical weight and mass measurements

    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
     laſſen
    -0.89
    oredCriteria
    -0.81
    <unused41>
    -0.73
    <unused8>
    -0.73
    <unused43>
    -0.73
    <unused47>
    -0.73
    <unused68>
    -0.73
    <unused79>
    -0.73
    [@BOS@]
    -0.72
    <unused3>
    -0.72
    POSITIVE LOGITS
     weight
    0.85
    Weight
    0.81
    weight
    0.81
     Weight
    0.76
     WEIGHT
    0.68
    WEIGHT
    0.67
     weigh
    0.67
     weighing
    0.66
    Weigh
    0.65
     weights
    0.63
    Activations Density 0.041%

    No Known Activations