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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8909
    Prev
    Next
    INDEX
    Explanations

    references to doors and door-related mechanisms or actions

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

    "door" (or its plural)

    np_acts-logits-general · gemini-2.0-flash

    door to door

    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
     متعلقه
    -0.68
    ]--;
    -0.65
    })));
    -0.55
    Билгалдахарш
    -0.55
    ettbewerb
    -0.54
    DRAM
    -0.54
    ftagPool
    -0.52
    ValueStyle
    -0.52
    ViewFeatures
    -0.51
    RetentionPolicy
    -0.51
    POSITIVE LOGITS
     doors
    0.96
     Doors
    0.94
     DOOR
    0.91
    door
    0.90
    Doors
    0.87
     doorways
    0.86
    teps
    0.86
    doors
    0.85
     door
    0.83
     Door
    0.82
    Activations Density 0.109%

    No Known Activations