© 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 EvalsExportsAPI 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. 29724
    Prev
    Next
    INDEX
    Explanations

    elements related to code structures and syntax

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

    approximately, as, boolean, return, expect, assert

    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
     m
    -0.44
    esgue
    -0.40
    폭
    -0.40
     wo
    -0.39
    omir
    -0.39
     =>
    -0.39
     (
    -0.37
    =>
    -0.37
    叙
    -0.37
    ً
    -0.36
    POSITIVE LOGITS
    IntoConstraints
    0.82
     onCancelled
    0.80
     betweenstory
    0.80
     fhew
    0.76
     الحره
    0.75
     Monfieur
    0.75
    ModelAdmin
    0.70
     onBackPressed
    0.69
     seiz
    0.69
    ArrowToggle
    0.67
    Activations Density 0.029%

    No Known Activations