© 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. 18-GEMMASCOPE-RES-16K
    11. 10963
    Prev
    Next
    INDEX
    Explanations

    phrases related to dining, seating arrangements, and views

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

    Desirable property features and amenities

    np_acts-logits-general · gemini-2.0-flash

    desirable spots with views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.73
    setIsLoading
    -0.56
    __':
    -0.54
    kmale
    -0.53
    __":
    -0.52
    afio
    -0.51
    ContentLoaded
    -0.49
     almuerzo
    -0.47
     нах
    -0.47
    lié
    -0.46
    POSITIVE LOGITS
     upgraded
    0.75
     upgrade
    0.70
    thâu
    0.70
     overlooking
    0.70
     corner
    0.69
     waterfront
    0.67
     upgrades
    0.65
     beachfront
    0.65
    upgrade
    0.61
    corner
    0.58
    Activations Density 0.056%

    No Known Activations