© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11597
    Prev
    Next
    INDEX
    Explanations

    code structures involving function definitions and closures

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

    Code snippets and code-related tokens

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks and delimiters

    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
     виправивши
    -0.73
     NSCoder
    -0.56
     the
    -0.56
    atista
    -0.56
     segar
    -0.56
     nélk
    -0.55
    CloseOperation
    -0.55
     fédé
    -0.52
    msgTypes
    -0.52
    pyplot
    -0.52
    POSITIVE LOGITS
    ↵↵
    0.62
    windowFixed
    0.57
    .)}
    0.55
    #+#
    0.52
    reditation
    0.50
    }*/
    0.48
    +}
    0.48
     Bunch
    0.47
     ""));
    0.47
    ]-->
    0.46
    Activations Density 0.323%

    No Known Activations