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. 3-GEMMASCOPE-RES-16K
    6. 10969
    Prev
    Next
    INDEX
    Explanations

    references to regulatory or legal rules and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.56
    ervious
    -0.55
    +</
    -0.53
     Hass
    -0.53
     Amad
    -0.52
     Abraham
    -0.52
     restrictions
    -0.52
    ?>
    
    -0.52
     Hartmann
    -0.52
     Hansen
    -0.51
    POSITIVE LOGITS
     Rule
    2.70
     RULE
    2.52
     rule
    2.52
    rule
    2.44
    Rule
    2.41
    RULE
    2.05
     getRule
    1.62
     règle
    1.29
    Regel
    1.16
     правило
    1.15
    Activations Density 0.087%

    No Known Activations