© 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. 366
    Prev
    Next
    INDEX
    Explanations

    details about property features and specifications

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

    Numbers followed by "bedrooms"

    np_acts-logits-general · gemini-2.0-flash

    bedrooms or beds

    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
     '\\;'
    -0.77
    waitKey
    -0.69
     kasarigan
    -0.69
     تضيفلها
    -0.68
     /\.(
    -0.62
     Chwiliwch
    -0.62
    devamını
    -0.61
     comuniques
    -0.60
     autorytatywna
    -0.60
    Tikang
    -0.60
    POSITIVE LOGITS
     bedrooms
    0.76
     bedroom
    0.70
     Bedroom
    0.58
     BEDROOM
    0.57
     Bedrooms
    0.56
    bed
    0.56
    bedroom
    0.56
     bedro
    0.56
     bedo
    0.50
    Bedroom
    0.50
    Activations Density 0.057%

    No Known Activations