© 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. 20-GEMMASCOPE-RES-16K
    11. 142
    Prev
    Next
    INDEX
    Explanations

    references to 'house' and its variations, indicating a focus on domestic or household themes

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

    "house" (household, house cleaning, etc.)

    np_acts-logits-general · gemini-2.0-flash

    house related entities

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    zelfde
    -0.64
     relati
    -0.62
     Egl
    -0.60
     homeward
    -0.59
     punctures
    -0.59
    kegaard
    -0.58
     panahon
    -0.58
     virginity
    -0.58
     ſever
    -0.57
     cavitation
    -0.57
    POSITIVE LOGITS
    wares
    0.83
    warming
    0.81
    mates
    0.79
    plants
    0.75
    keepers
    0.72
    plant
    0.70
    HOLD
    0.65
    boat
    0.64
     tangga
    0.61
     houses
    0.60
    Activations Density 0.114%

    No Known Activations