© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 8626
    Prev
    Next
    INDEX
    Explanations

    code-related terms and comments related to warnings and errors in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.84
     surla
    -0.74
     '\\;'
    -0.66
     AssemblyTitle
    -0.64
    oredCriteria
    -0.63
    DockStyle
    -0.62
     Biôgrafia
    -0.60
    BufferException
    -0.59
    ſelf
    -0.58
     Wicidata
    -0.57
    POSITIVE LOGITS
    SuppressMessage
    0.64
    SuppressLint
    0.64
    SuppressWarnings
    0.63
    noinspection
    0.60
     noqa
    0.58
     Warning
    0.49
     warning
    0.46
    Warning
    0.43
    eslint
    0.43
     eslint
    0.42
    Activations Density 0.195%

    No Known Activations