© 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. 22-GEMMASCOPE-RES-16K
    11. 326
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to layer deposition processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "thin" followed by "layer" or related terms

    np_acts-logits-general · gemini-2.0-flash

    thin layers or films

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.92
     FetchType
    -0.73
     ivelany
    -0.72
    TagMode
    -0.68
    RenderAtEndOf
    -0.64
    IntoConstraints
    -0.63
    posedge
    -0.58
    quelize
    -0.55
    ConstraintMaker
    -0.54
    PreInfinity
    -0.54
    POSITIVE LOGITS
     layer
    2.65
     layers
    2.42
    layer
    2.25
     Layer
    2.22
    Layer
    2.08
     thickness
    2.08
     LAYER
    2.05
     Layers
    2.02
     thin
    1.92
    layers
    1.83
    Activations Density 0.657%

    No Known Activations