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. 12-GEMMASCOPE-RES-16K
    6. 9416
    Prev
    Next
    INDEX
    Explanations

    references to reasons and justifications behind actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    šanu
    -0.49
     zugelassen
    -0.45
    gerichte
    -0.43
     I
    -0.43
    zugehen
    -0.43
     adi
    -0.41
     dành
    -0.41
     contra
    -0.40
     Finley
    -0.39
    voe
    -0.39
    POSITIVE LOGITS
     why
    1.46
     reasons
    1.44
    reasons
    1.33
     reason
    1.33
    Reasons
    1.30
     Reasons
    1.29
     REASONS
    1.29
    why
    1.27
     WHY
    1.17
    reason
    1.17
    Activations Density 0.517%

    No Known Activations