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. 10956
    Prev
    Next
    INDEX
    Explanations

    terms related to intersections, overlaps, and connections in various contexts

    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
     væ
    -0.65
    oob
    -0.63
     Cyber
    -0.60
     echar
    -0.60
     aDecoder
    -0.59
     hånd
    -0.57
    ΤΑ
    -0.57
     tư
    -0.56
     bekym
    -0.56
     procédure
    -0.55
    POSITIVE LOGITS
     intersection
    2.96
     intersections
    2.61
     Intersection
    2.56
    intersection
    2.38
    Intersection
    2.36
     intersect
    2.18
     intersected
    1.93
     intersects
    1.87
     intersecting
    1.85
     interse
    1.81
    Activations Density 0.127%

    No Known Activations