© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2406
    Prev
    Next
    INDEX
    Explanations

    components related to formatting and output specifications

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

    formatting specification strings and their components (format specifiers, delimiters, and numeric patterns).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.66
     يتيمه
    -0.62
    sidemargin
    -0.51
     nahilalakip
    -0.50
     tabs
    -0.49
    principalColumn
    -0.48
     Tabs
    -0.47
     насељу
    -0.45
     poveznice
    -0.44
     tab
    -0.43
    POSITIVE LOGITS
     format
    1.02
    format
    1.00
     Format
    0.96
     formats
    0.93
     FORMAT
    0.92
     formatted
    0.91
    Format
    0.89
     Formats
    0.89
     formatting
    0.85
    FORMAT
    0.84
    Activations Density 0.258%

    No Known Activations