Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14710
    Prev
    Next
    INDEX
    Explanations

    references to living rooms and their characteristics

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

    "living room" or "dining room"

    np_acts-logits-general · gemini-2.0-flash

    living room and dining room

    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
     betweenstory
    -0.89
     ویکی‌پدیای
    -0.83
     bezeichneter
    -0.80
     صوتيه
    -0.71
     فريبيس
    -0.71
    ViewFeatures
    -0.67
     дописавши
    -0.66
    GEBURTSDATUM
    -0.64
    BoxShadow
    -0.64
    EndInit
    -0.63
    POSITIVE LOGITS
     dining
    0.81
     living
    0.79
     Dining
    0.72
    dining
    0.69
    living
    0.68
     downstairs
    0.67
    sbereich
    0.67
     Living
    0.66
    Dining
    0.64
    Living
    0.63
    Activations Density 0.023%

    No Known Activations