© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 10292
    Prev
    Next
    INDEX
    Explanations

    specific references to the term "bare" and its variations in relation to context, especially in connection with Singapore and optical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Persson
    -0.52
     hendes
    -0.50
     suaminya
    -0.48
     Parigi
    -0.48
     paille
    -0.47
     Arce
    -0.47
     Figue
    -0.47
     Bekasi
    -0.46
     Barbier
    -0.46
     presidential
    -0.46
    POSITIVE LOGITS
     Alumni
    0.62
     alumni
    0.56
    PreferredItem
    0.55
    AutoField
    0.52
    Alumni
    0.50
     bare
    0.46
    cault
    0.46
    }<\
    0.44
    dflare
    0.43
    Bare
    0.43
    Activations Density 0.380%

    No Known Activations