© 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. 24-GEMMASCOPE-RES-16K
    11. 13821
    Prev
    Next
    INDEX
    Explanations

    references to the word "house" and related terms in various contexts

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

    "House" followed by occupations or activities

    np_acts-logits-general · gemini-2.0-flash

    house compound phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     panahon
    -0.55
    enciales
    -0.54
    road
    -0.52
     Silence
    -0.51
    tagHelperRunner
    -0.51
    Silence
    -0.50
    zelfde
    -0.49
    OMON
    -0.48
     masas
    -0.48
     PARKER
    -0.47
    POSITIVE LOGITS
    warming
    0.84
    wares
    0.83
    plants
    0.79
    HOLD
    0.76
    hould
    0.75
    boat
    0.73
    guests
    0.71
    cleaning
    0.69
    keepers
    0.69
    boats
    0.69
    Activations Density 0.085%

    No Known Activations