© 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. 82741
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the structure and organization of data and models

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

    for each, for the, for every

    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
    derive
    -0.28
    
    -0.27
    TRAILING
    -0.27
    JAKARTA
    -0.26
    setHorizontal
    -0.25
     επ
    -0.25
     utilizar
    -0.24
    ͖
    -0.24
     الاطلاع
    -0.24
     utiliza
    -0.23
    POSITIVE LOGITS
     autorytatywna
    0.80
    󠁣
    0.80
    yntaxException
    0.77
     sumpay
    0.68
     Geſch
    0.67
     increí
    0.66
     $_"
    0.66
    OGND
    0.65
     erſt
    0.65
     $_(
    0.64
    Activations Density 0.178%

    No Known Activations