© 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. 20-GEMMASCOPE-RES-131K
    6. 95373
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific species of moths

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

    emergence, feeding, and recovery stages

    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
    ])):
    -0.36
    流石
    -0.36
     lap
    -0.35
     cabbage
    -0.35
     cats
    -0.35
     cat
    -0.34
     enfans
    -0.34
     formula
    -0.34
     shipping
    -0.34
     fine
    -0.34
    POSITIVE LOGITS
     utafitiHapana
    0.70
     propOrder
    0.64
     Autorisations
    0.55
    Tikang
    0.54
    +#+
    0.53
    +#+#
    0.53
     Autorizaciones
    0.53
    fromnode
    0.52
    :✨
    0.51
    aarrggbb
    0.51
    Activations Density 0.093%

    No Known Activations