© 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. 22-GEMMASCOPE-RES-16K
    11. 8998
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their results in programming contexts

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

    Numbers before or after a dash

    np_acts-logits-general · gemini-2.0-flash

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fifty
    -0.81
    Fifty
    -0.80
     Forty
    -0.74
     hundred
    -0.73
    Forty
    -0.71
     Thirty
    -0.70
    Thirty
    -0.69
     Sixty
    -0.68
    fifty
    -0.66
     Hundred
    -0.64
    POSITIVE LOGITS
     eight
    1.48
     nine
    1.45
     seven
    1.44
     six
    1.29
     Eight
    1.18
    eight
    1.15
    Eight
    1.13
     ten
    1.11
    seven
    1.10
     NINE
    1.08
    Activations Density 1.731%

    No Known Activations