© 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. 37581
    Prev
    Next
    INDEX
    Explanations

    assertions or expected outcomes in a coding or testing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    الحياه
    -0.65
    transQ
    -0.54
    PMailer
    -0.51
    CROSSTALK
    -0.49
    __::
    -0.48
    boutin
    -0.46
    ('-'
    -0.46
    ftagPool
    -0.46
    IGraphics
    -0.44
    [++
    -0.44
    POSITIVE LOGITS
     useState
    2.14
    useState
    1.85
     useRef
    0.72
     useCallback
    0.64
     BehaviorSubject
    0.63
    useEffect
    0.60
     useEffect
    0.59
     initState
    0.58
     makeStyles
    0.54
    GOTREF
    0.53
    Activations Density 0.000%

    No Known Activations