© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6595
    Prev
    Next
    INDEX
    Explanations

    elements related to string manipulation, particularly those involving commas and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ")";
    -0.59
     ")"
    -0.59
     referenties
    -0.52
    housie
    -0.51
    zm
    -0.50
    #+#
    -0.50
    RegressionTest
    -0.50
    koop
    -0.50
    Зноскі
    -0.49
    ">//
    -0.47
    POSITIVE LOGITS
    (',',
    1.17
     comma
    1.11
     commas
    1.09
    Comma
    1.08
    comma
    1.00
    (',
    0.97
    (",",
    0.95
     Csv
    0.87
    (',');
    0.86
    COMMA
    0.81
    Activations Density 0.214%

    No Known Activations