© 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. 31-GEMMASCOPE-RES-16K
    11. 8909
    Prev
    Next
    INDEX
    Explanations

    references to dates, events, and societal issues

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

    dates and numerical sequences, particularly years, months, and day numbers.

    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
    January
    -0.73
     January
    -0.73
     December
    -0.71
    February
    -0.71
    December
    -0.70
     CHRISTMAS
    -0.70
     February
    -0.69
     November
    -0.69
    November
    -0.68
    Winter
    -0.66
    POSITIVE LOGITS
     summer
    1.65
     July
    1.65
    July
    1.60
    summer
    1.48
     Summer
    1.48
    JULY
    1.47
    Summer
    1.45
     JULY
    1.44
    july
    1.38
     july
    1.37
    Activations Density 0.356%

    No Known Activations