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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2635
    Prev
    Next
    INDEX
    Explanations

    code related to storage operations and data structures in programming

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

    code-related syntax and programming language constructs, particularly in Swift or protobuf-like languages.

    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
    por
    -0.42
     enriched
    -0.41
     customised
    -0.39
     Robertson
    -0.38
     sceptical
    -0.38
     Por
    -0.38
     because
    -0.38
    ziehungs
    -0.37
     safer
    -0.37
     execution
    -0.37
    POSITIVE LOGITS
    OrBuilder
    0.75
     ब्रेकडाउन
    0.63
    parsedMessage
    0.61
    WireFormatLite
    0.59
    kháu
    0.58
     MainAxisSize
    0.57
    bitField
    0.57
    AccessorTable
    0.56
     Monfieur
    0.56
    帖最后由
    0.56
    Activations Density 0.354%

    No Known Activations