© 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. 24-GEMMASCOPE-RES-16K
    11. 4227
    Prev
    Next
    INDEX
    Explanations

    references to legal codes, acts, and regulations

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

    specific Acts or sections

    np_acts-logits-general · gemini-2.0-flash

    enacted or assigned act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.71
     muualla
    -0.53
     colspan
    -0.50
    ंदीखरीदारी
    -0.50
    icioso
    -0.47
     lighter
    -0.47
    Suggested
    -0.47
     darker
    -0.47
    aggia
    -0.46
    koning
    -0.43
    POSITIVE LOGITS
     dated
    0.98
     promulgated
    0.82
     passed
    0.75
     enacted
    0.73
     issued
    0.72
     DATED
    0.69
    dated
    0.69
     published
    0.69
    Capítulo
    0.64
     بتاريخ
    0.62
    Activations Density 0.703%

    No Known Activations