© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2179
    Prev
    Next
    INDEX
    Explanations

    the start of a document or section

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

    Windows and wins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     propOrder
    -1.00
     mergeFrom
    -0.93
    TestBed
    -0.74
     AttributeSet
    -0.70
    AddTagHelper
    -0.70
     متعلقه
    -0.65
    SharedDtor
    -0.63
     MotionEvent
    -0.62
    +#+#
    -0.62
    ensement
    -0.62
    POSITIVE LOGITS
     preci
    0.51
    ########.
    0.50
    Windows
    0.48
    Win
    0.46
     Win
    0.45
     newState
    0.45
    Wins
    0.45
    rosh
    0.44
    WIN
    0.44
    wins
    0.44
    Activations Density 0.002%

    No Known Activations