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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14353
    Prev
    Next
    INDEX
    Explanations

    details related to housing and property features

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

    Mention of bathrooms or bedrooms

    np_acts-logits-general · gemini-2.0-flash

    bathroom

    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
    Personendaten
    -0.78
    saraba
    -0.76
    Билгалдахарш
    -0.58
    VELAND
    -0.54
    tvguidetime
    -0.54
    رشف
    -0.53
    WireFormatLite
    -0.53
     nonUne
    -0.51
    Rüyada
    -0.50
    WireFormat
    -0.50
    POSITIVE LOGITS
     bathroom
    1.56
     bathrooms
    1.53
     Bathroom
    1.33
     Bathrooms
    1.28
    Bathroom
    1.26
    Bathrooms
    1.24
    bathroom
    1.23
     BATH
    1.22
     baño
    1.21
     bath
    1.14
    Activations Density 0.068%

    No Known Activations