© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9407
    Prev
    Next
    INDEX
    Explanations

    points in 2D coordinate systems, specifically related to geometric transformations

    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
    arwal
    -0.65
    tshell
    -0.65
     Rivas
    -0.61
     AssemblyTitle
    -0.60
     Cud
    -0.59
     MainAxisSize
    -0.58
     "")
    -0.57
    addFlags
    -0.57
    )?;
    -0.57
    ctis
    -0.56
    POSITIVE LOGITS
    Point
    1.68
     Point
    1.53
    POINT
    1.39
    point
    1.38
     POINT
    1.37
    points
    1.24
     Pointe
    1.19
     Points
    1.12
    Points
    1.11
    pointe
    1.07
    Activations Density 0.085%

    No Known Activations