© 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. 2696
    Prev
    Next
    INDEX
    Explanations

    programming comments and annotations related to code generation or documentation

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

    code-related terms like "TODO", "method", "generated", and other programming syntax elements.

    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
     wikipagina
    -0.57
     թվական
    -0.45
    Kanpo
    -0.44
     myſelf
    -0.42
    protoimpl
    -0.42
    yarnpkg
    -0.42
    elemField
    -0.42
     disfraces
    -0.42
     Wikiseite
    -0.41
     pleaſure
    -0.40
    POSITIVE LOGITS
    yntaxException
    0.65
     getItemCount
    0.60
    URLException
    0.56
     []:
    0.52
    ActionPerformed
    0.51
     Stel
    0.50
     Kom
    0.50
    دانشنامهٔ
    0.49
     referenties
    0.47
    '}';
    0.46
    Activations Density 0.023%

    No Known Activations