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. 16-GEMMASCOPE-RES-16K
    6. 6098
    Prev
    Next
    INDEX
    Explanations

    elements and features related to urban development and real estate

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

    Features or components of vehicles/devices

    np_acts-logits-general · gemini-2.0-flash

    parts features components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.39
    ValueStyle
    -1.36
     myſelf
    -1.27
     Houſe
    -1.24
     themſelves
    -1.20
    Personensuche
    -1.18
     purpoſe
    -1.18
     houſe
    -1.17
     ſeveral
    -1.16
     Theſe
    -1.16
    POSITIVE LOGITS
     plus
    0.88
     and
    0.71
     
    0.70
     to
    0.68
    ,
    0.66
     in
    0.64
    plus
    0.61
    Plus
    0.60
     Plus
    0.59
     (
    0.59
    Activations Density 0.218%

    No Known Activations