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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2160
    Prev
    Next
    INDEX
    Explanations

    references to edges in a geometric or graph context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.48
    Бахар
    -0.37
    Televis
    -0.36
     Gaspar
    -0.34
    المكان
    -0.32
     Ketten
    -0.32
    haikusbot
    -0.31
    IBAction
    -0.31
    hoeddwyd
    -0.31
     tand
    -0.30
    POSITIVE LOGITS
     edge
    2.53
     edges
    2.48
     border
    2.22
    edge
    2.13
     Edges
    2.11
     Edge
    2.08
    Edge
    2.06
     borders
    2.02
    edges
    1.95
     EDGE
    1.90
    Activations Density 0.281%

    No Known Activations