© 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. 20-GEMMASCOPE-RES-16K
    6. 14283
    Prev
    Next
    INDEX
    Explanations

    special character sequences often used in statistical or technical contexts, particularly involving structured data or formulas

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

    The neuron detects statistical significance markers (typically "**" or asterisks) in tables and mathematical notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    AndEndTag
    -0.64
     initComponents
    -0.60
     forState
    -0.57
    󠁿
    -0.57
     estekak
    -0.57
    tagHelperRunner
    -0.56
     wireType
    -0.53
    msgTypes
    -0.52
    ;';
    -0.52
    ThroughAttribute
    -0.51
    POSITIVE LOGITS
    underbrace
    0.37
    WillAppear
    0.36
    boxed
    0.36
    RemoveField
    0.35
    Embeddable
    0.34
     [*]
    0.33
     PeEnEo
    0.33
    
    0.33
     Rs
    0.32
     Tint
    0.32
    Activations Density 0.484%

    No Known Activations