© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28282
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating the effectiveness and quality of design or execution in various contexts

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

    design and architecture

    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
     demografica
    -0.40
     Commissione
    -0.40
    OrEqual
    -0.37
    FunctionType
    -0.36
    λικ
    -0.35
     Komis
    -0.35
    ClassId
    -0.34
     scammer
    -0.34
     beep
    -0.34
    flich
    -0.34
    POSITIVE LOGITS
     design
    0.59
     diseño
    0.57
    exitRule
    0.56
    designed
    0.55
     designer
    0.53
    rizona
    0.53
     designers
    0.53
     tasarım
    0.52
     ontwerp
    0.52
     designed
    0.52
    Activations Density 0.006%

    No Known Activations