© 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. 2662
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their associated operations

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

    code-related syntax and operations, particularly references to variables, methods, and programming constructs.

    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
    
    -0.33
    Yet
    -0.31
    Added
    -0.30
     המע
    -0.30
     Exact
    -0.29
    Here
    -0.29
    Asie
    -0.29
    CONTEXT
    -0.29
     anum
    -0.29
    UserContext
    -0.28
    POSITIVE LOGITS
    +#+#
    0.70
    parsedMessage
    0.69
    ArrowToggle
    0.69
    rrggbb
    0.67
    exitRule
    0.63
     autorytatywna
    0.63
    DotNetBar
    0.63
     ویکی‌پدی
    0.62
     CreateTagHelper
    0.61
    titleMargin
    0.61
    Activations Density 0.796%

    No Known Activations