© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 311
    Prev
    Next
    INDEX
    Explanations

    elements related to actions involving knocking on doors and interactions at doorsteps

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

    occurrences of suspenseful sounds or actions

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

    knocking on doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    plc
    -0.58
     Flucht
    -0.48
     Estelle
    -0.48
    continence
    -0.47
    dzi
    -0.47
    mitter
    -0.47
     Paralymp
    -0.47
    defn
    -0.46
     substring
    -0.45
    tenham
    -0.44
    POSITIVE LOGITS
     knocking
    1.14
     doorbell
    1.09
     knock
    1.08
     knocks
    1.04
    Knock
    1.01
    knock
    0.96
     Knock
    0.93
     summons
    0.89
     knocked
    0.86
     door
    0.83
    Activations Density 0.093%

    No Known Activations