© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 15929
    Prev
    Next
    INDEX
    Explanations

    geometric properties and parameters related to shapes and structures, particularly in a circular or cylindrical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fass
    -0.60
     Trist
    -0.59
     tri
    -0.51
     Lettuce
    -0.50
     Wainwright
    -0.50
     κατά
    -0.50
    Chains
    -0.49
    TableModel
    -0.49
     ProtoMessage
    -0.49
    rophoto
    -0.49
    POSITIVE LOGITS
     circles
    1.34
     circle
    1.27
     radius
    1.23
     diameter
    1.19
     Circles
    1.19
     Diameter
    1.19
    circles
    1.15
    radius
    1.14
    circle
    1.12
    diameter
    1.12
    Activations Density 0.517%

    No Known Activations