© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31565
    Prev
    Next
    INDEX
    Explanations

    elements associated with navigation and user interface components

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

    legal citations and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bery
    -0.47
    glPushMatrix
    -0.46
    PostExecute
    -0.45
    Хро
    -0.44
    millimeters
    -0.44
    inata
    -0.43
    EventLoop
    -0.43
     couple
    -0.41
     holding
    -0.40
    ValueMap
    -0.40
    POSITIVE LOGITS
    rawDesc
    0.77
    SourceChecksum
    0.74
    paravant
    0.73
     kasarigan
    0.72
    BeginContext
    0.69
    awtextra
    0.67
    ⓧ
    0.66
    matchCondition
    0.65
    protoc
    0.65
    Tikang
    0.64
    Activations Density 0.055%

    No Known Activations