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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23080
    Prev
    Next
    INDEX
    Explanations

    components and mechanics related to moving parts in toys or engineering

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

    robots, electric motors, tricks

    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
     Nachhaltigkeit
    -0.43
     للمعارف
    -0.42
    
    -0.38
     workload
    -0.37
    ificazione
    -0.36
     Leighton
    -0.35
     Frieden
    -0.35
     Landschaft
    -0.35
     świad
    -0.34
    stylesheet
    -0.34
    POSITIVE LOGITS
    oredCriteria
    0.73
    MLLoader
    0.63
     ModelExpression
    0.59
    PropertyChanging
    0.53
     SwitchCompat
    0.51
     Roskov
    0.50
    pulumi
    0.48
     pollut
    0.47
    internalType
    0.47
    twimg
    0.47
    Activations Density 0.019%

    No Known Activations