© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15639
    Prev
    Next
    INDEX
    Explanations

    instances of the word "door" and related references throughout the text

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

    "door" or "doors"

    np_acts-logits-general · gemini-2.0-flash

    door and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obno
    -0.39
     Beobach
    -0.39
    astan
    -0.37
     mediano
    -0.37
    s
    -0.36
    SerializeField
    -0.36
    weakSelf
    -0.36
     scientifique
    -0.35
     fija
    -0.35
    滯
    -0.35
    POSITIVE LOGITS
     Door
    1.54
     DOOR
    1.48
    Door
    1.46
     door
    1.45
     Doors
    1.45
     doors
    1.40
    door
    1.34
    Doors
    1.30
    doors
    1.27
     Türen
    1.19
    Activations Density 0.070%

    No Known Activations