© 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. 116534
    Prev
    Next
    INDEX
    Explanations

    negative words or phrases

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

    mg m^−2^ dosing units

    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
     فريبيس
    -0.93
    tagHelperRunner
    -0.90
    存于互联网档案馆
    -0.83
     تضيفلها
    -0.79
     ſind
    -0.76
     ExecuteAsync
    -0.76
     CreateTagHelper
    -0.75
     ब्रेकडाउन
    -0.75
     nahilalakip
    -0.75
     AssemblyVersion
    -0.74
    POSITIVE LOGITS
    ️
    0.95
    ‍♂️
    0.69
    🏼
    0.66
    ‍♀️
    0.65
    🏻
    0.61
    🏽
    0.60
    ing
    0.58
    🏾
    0.55
    t
    0.54
    s
    0.49
    Activations Density 0.007%

    No Known Activations