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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2905
    Prev
    Next
    INDEX
    Explanations

    descriptions of residential spaces and amenities

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

    bathrooms or restrooms

    np_acts-logits-general · gemini-2.0-flash

    bathroom or restrooms

    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
    ysuckle
    -0.53
    ]})
    -0.52
    saraba
    -0.49
     Himo
    -0.48
    cinia
    -0.48
    loit
    -0.46
    Witam
    -0.45
     fré
    -0.45
    india
    -0.44
     cod
    -0.44
    POSITIVE LOGITS
     bathroom
    1.82
     bathrooms
    1.71
     Bathroom
    1.58
    bathroom
    1.47
     Bathrooms
    1.44
    Bathroom
    1.42
     BATH
    1.36
    Bathrooms
    1.35
     bath
    1.34
     baño
    1.34
    Activations Density 0.090%

    No Known Activations