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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104828
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Билгалдахарш
    -0.43
    httphttps
    -0.39
    ţele
    -0.37
    曖昧さ回避
    -0.35
    ⓧ
    -0.35
    canestro
    -0.34
    Искәрмәләр
    -0.34
    uspiel
    -0.34
     happened
    -0.34
    angkutan
    -0.33
    POSITIVE LOGITS
    economic
    0.45
     nul
    0.44
    spinal
    0.44
    centiles
    0.44
    存于互联网档案馆
    0.44
    MVH
    0.43
    setViewportView
    0.43
     lobby
    0.43
     ModelExpression
    0.43
     OFDb
    0.42
    Activations Density 0.025%

    No Known Activations