© 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. 24-GEMMASCOPE-RES-16K
    11. 6441
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming syntax and function definitions

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

    Diff output code snippets

    np_acts-logits-general · gemini-2.0-flash

    git diff markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.63
    Transcripción
    -0.60
    kháu
    -0.54
    principalColumn
    -0.53
    ագրություններ
    -0.53
    StoryboardSegue
    -0.51
    NameInMap
    -0.50
    neſs
    -0.50
     resourceCulture
    -0.49
     hasNext
    -0.48
    POSITIVE LOGITS
    @@
    1.28
    +
    0.99
    <eos>
    0.95
    +#
    0.78
    +}
    0.77
    )+
    0.73
    +$
    0.72
    +<
    0.70
     @@
    0.69
    diff
    0.69
    Activations Density 0.211%

    No Known Activations