© 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. 3321
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and bindings

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

    code-related keywords, particularly from programming languages like Rust and WebAssembly.

    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
     betweenstory
    -0.80
    IntoConstraints
    -0.62
     initComponents
    -0.62
     mijne
    -0.59
    transQ
    -0.58
    +#+#
    -0.57
    SequentialGroup
    -0.57
    脚注の使い方
    -0.56
    RegressionTest
    -0.56
    ########.
    -0.54
    POSITIVE LOGITS
    DataAnnotations
    0.62
     ComVisible
    0.51
    DllImport
    0.49
    subsection
    0.46
    Билгалдахарш
    0.42
    SuppressMessage
    0.42
     label
    0.41
     free
    0.41
     lenker
    0.41
     counter
    0.40
    Activations Density 0.091%

    No Known Activations