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. 38202
    Prev
    Next
    INDEX
    Explanations

    terms related to quantity and valuation

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

    size and comparison

    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
     invokingState
    -0.44
    出版年
    -0.33
    合わせ
    -0.32
    合わせて
    -0.31
    ViewFeatures
    -0.30
     likewise
    -0.30
     igualmente
    -0.30
    
    -0.29
    IBarButtonItem
    -0.29
     betweenstory
    -0.29
    POSITIVE LOGITS
     للمعارف
    0.88
    ConstraintMaker
    0.82
    SequentialGroup
    0.79
     myſelf
    0.79
    niſſe
    0.74
     beſte
    0.73
     laſſen
    0.72
     ſind
    0.71
    ſſung
    0.68
     ſoll
    0.68
    Activations Density 0.115%

    No Known Activations