Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3055
    Prev
    Next
    INDEX
    Explanations

    references to dates and calendar-related terms

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

    French months

    np_acts-logits-general · gemini-2.0-flash

    months and after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.49
    ,
    -0.49
    使
    -0.49
    getSource
    -0.44
    -
    -0.43
    :
    -0.42
     (
    -0.42
    3
    -0.41
    5
    -0.41
     âgées
    -0.40
    POSITIVE LOGITS
     تانيه
    1.29
    SharedDtor
    1.07
     nakalista
    1.05
     незавершена
    1.03
    RectangleBorder
    1.01
    addCriterion
    0.96
    Бахар
    0.96
     Signalez
    0.95
     transfieras
    0.95
     समीक्षक
    0.92
    Activations Density 0.124%

    No Known Activations