© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8828
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and indices predominantly found in programming contexts

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

    Code snippets with indexing/looping

    np_acts-logits-general · gemini-2.0-flash

    code loops and variables

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     חיצוניים
    -0.70
     архивлан
    -0.70
    ----</
    -0.70
    ')],
    -0.69
    '])->
    -0.69
    ]]=
    -0.68
    ագրություններ
    -0.66
    ']));
    -0.66
    }]{
    -0.66
    )}</
    -0.66
    POSITIVE LOGITS
     Estadual
    0.50
     Constitucional
    0.49
     literaria
    0.49
     लेकर
    0.49
    UpInside
    0.48
     Públicas
    0.47
     CreateTagHelper
    0.47
    AddTagHelper
    0.47
     until
    0.45
     jusqu
    0.45
    Activations Density 0.036%

    No Known Activations