© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102928
    Prev
    Next
    INDEX
    Explanations

    programming or coding-related elements, specifically syntax and function calls in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ſeveral
    -0.72
    OCCURRED
    -0.71
     $_(
    -0.69
     Monfieur
    -0.69
     myſelf
    -0.66
     Majefty
    -0.65
    iſche
    -0.65
    iſchen
    -0.65
     OMITBAD
    -0.65
    InitVars
    -0.64
    POSITIVE LOGITS
     sc
    0.28
     Ch
    0.28
    JButton
    0.25
     то
    0.24
     Kub
    0.23
    marvin
    0.23
    ubarak
    0.23
    obacter
    0.22
     غ
    0.22
     Apply
    0.22
    Activations Density 0.003%

    No Known Activations