© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 93292
    Prev
    Next
    INDEX
    Explanations

    phrases indicating simplicity or efficiency in processes or methods

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

    simplified and simple concepts

    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
     Bowers
    -0.42
     الكم
    -0.41
    دانشنامهٔ
    -0.38
    shall
    -0.36
     sover
    -0.36
     Roz
    -0.36
     themſelves
    -0.34
    InternalFrame
    -0.34
    ordinateur
    -0.34
     растя
    -0.34
    POSITIVE LOGITS
    ArrowToggle
    0.74
     simplified
    0.72
     simpler
    0.63
     simplicity
    0.62
    bootstrapcdn
    0.59
     simple
    0.59
    simplified
    0.57
     simplify
    0.57
     simpli
    0.56
    Simple
    0.56
    Activations Density 0.270%

    No Known Activations