© 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. 80428
    Prev
    Next
    INDEX
    Explanations

    colors and materials associated with vehicle design

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

    black, satin, titanium, poplar describing appearance

    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
    ModelMap
    -0.48
     '\\;'
    -0.46
    Gambas
    -0.46
     combineReducers
    -0.43
     onCancelled
    -0.40
    Boxscore
    -0.40
    HXLINE
    -0.39
    UnitTesting
    -0.39
    GOTREF
    -0.39
    #+#
    -0.38
    POSITIVE LOGITS
     besk
    0.44
     igjen
    0.43
    løs
    0.42
    Aholisi
    0.39
     trim
    0.39
     SOLUTIONS
    0.38
     included
    0.38
     INCLUD
    0.37
    piew
    0.37
     обли
    0.37
    Activations Density 0.059%

    No Known Activations