© 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. 96407
    Prev
    Next
    INDEX
    Explanations

    references to time, quantity, and comparisons in descriptions

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

    at specific times, levels, scales

    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
     initComponents
    -0.58
    ChildScrollView
    -0.54
    antaranya
    -0.52
    ParallelGroup
    -0.49
     Vikipedi
    -0.47
     dirait
    -0.46
    UserScript
    -0.46
    Mold
    -0.46
     modificaciones
    -0.45
    tanleria
    -0.44
    POSITIVE LOGITS
     at
    0.78
     At
    0.71
    At
    0.61
     level
    0.59
     point
    0.56
     locations
    0.54
     points
    0.54
     rate
    0.53
    elementAt
    0.52
     location
    0.51
    Activations Density 0.122%

    No Known Activations