© 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. 20-GEMMASCOPE-RES-65K
    11. 3923
    Prev
    Next
    INDEX
    Explanations

    terms related to modifying attributes and settings in a coding or assembly context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    license or pay

    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
    Negative Logits
    openSession
    -0.46
     ✓
    -0.45
     Brown
    -0.44
    vosti
    -0.43
    Kariera
    -0.43
     estekak
    -0.40
     atom
    -0.40
    Lea
    -0.39
    IF
    -0.39
    andr
    -0.39
    POSITIVE LOGITS
    CloseOperation
    0.77
     CreateTagHelper
    0.75
    Autoritní
    0.72
    $_['
    0.70
    =$?
    0.70
     propOrder
    0.69
    __":
    0.69
    '},
    0.67
    دانشنامهٔ
    0.67
    IntoConstraints
    0.66
    Activations Density 0.030%

    No Known Activations