© 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. 121214
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to procedural errors in judicial contexts

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

    failure to act

    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
    ๆ
    -0.49
     насељу
    -0.46
    WebVitals
    -0.45
     generously
    -0.43
    fra
    -0.43
    IActionResult
    -0.43
     ObjectParameter
    -0.43
    Dermott
    -0.42
    GIVEREF
    -0.40
    bil
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.43
    IntoConstraints
    0.40
     gereken
    0.38
     Administrativna
    0.38
    autoIncrement
    0.38
     advirtió
    0.36
    ChildScrollView
    0.35
    limsy
    0.35
    URLException
    0.35
     légales
    0.35
    Activations Density 0.125%

    No Known Activations