© 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. 2325
    Prev
    Next
    INDEX
    Explanations

    phrases related to data structures and their attributes in programming contexts

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

    technical programming-related words and commands, particularly around variable lists, code functions, and computational tasks.

    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
    HasAnnotation
    -0.38
     Vict
    -0.36
    Kjelder
    -0.34
     Seward
    -0.33
    tap
    -0.33
     giusta
    -0.33
    backtracking
    -0.33
    transQ
    -0.32
     fusca
    -0.31
    PageRoute
    -0.31
    POSITIVE LOGITS
    SharedDtor
    0.68
    elemField
    0.63
    </tfoot>
    0.55
    XMLSchema
    0.52
    autant
    0.51
    writeFieldEnd
    0.50
    .*")]
    0.49
     kasarigan
    0.48
    makeConstraints
    0.48
    RTCK
    0.47
    Activations Density 0.297%

    No Known Activations