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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2015
    Prev
    Next
    INDEX
    Explanations

    geometric and mathematical concepts related to vertices, coordinates, and projections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Citiți
    -0.37
    :✨
    -0.36
    insegna
    -0.36
     veiks
    -0.36
     manageable
    -0.35
     cartón
    -0.35
     kemasan
    -0.35
     trekken
    -0.35
     vastaan
    -0.35
    ERVIEW
    -0.35
    POSITIVE LOGITS
     point
    0.62
     vertices
    0.59
    point
    0.59
     точка
    0.59
    Point
    0.58
     MotionEvent
    0.58
     points
    0.55
     Point
    0.55
     CGPoint
    0.55
     POINT
    0.53
    Activations Density 1.100%

    No Known Activations