© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2195
    Prev
    Next
    INDEX
    Explanations

    function calls and data structure manipulations in code

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

    code tokens related to function or method names and their parameters.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    RegressionTest
    -0.65
    endphp
    -0.58
    endforeach
    -0.56
     AssemblyCulture
    -0.49
     Autorizaciones
    -0.46
     propOrder
    -0.44
     endfor
    -0.43
    URIComponent
    -0.43
    transQ
    -0.42
    MergeFrom
    -0.42
    POSITIVE LOGITS
     infeliz
    0.49
     uniquement
    0.45
     seulement
    0.44
    žiai
    0.42
     Comunicação
    0.42
     niestety
    0.41
     ویکی‌پدی
    0.41
    gebäude
    0.41
     Vereine
    0.41
     fortfarande
    0.41
    Activations Density 0.082%

    No Known Activations