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

    Neuronpedia

    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. 9-GEMMASCOPE-RES-16K
    11. 5458
    Prev
    Next
    INDEX
    Explanations

    references to doors and entrances, particularly in the context of their functionality and types

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

    "door" and its variations

    np_acts-logits-general · gemini-2.0-flash

    door and doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.63
     становника
    -0.59
    parsedMessage
    -0.58
    geç
    -0.54
    şört
    -0.54
    
    -0.53
    iNdEx
    -0.53
     Exacts
    -0.53
    Kalb
    -0.52
     WaitForSeconds
    -0.52
    POSITIVE LOGITS
     door
    1.51
     doors
    1.51
     DOOR
    1.36
     Door
    1.34
     Doors
    1.30
    Door
    1.29
    door
    1.27
    doors
    1.23
    Doors
    1.23
     Türen
    1.08
    Activations Density 0.149%

    No Known Activations