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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16210
    Prev
    Next
    INDEX
    Explanations

    situations involving hospitals and feelings of vulnerability or confinement

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

    descriptions of being physically located in a specific place or position.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aufenthalt
    -0.46
    Notae
    -0.41
     caminhada
    -0.40
     uyar
    -0.39
     Spazier
    -0.39
     Anliegen
    -0.37
    ឲ
    -0.36
     pemasangan
    -0.36
     zůst
    -0.36
    relser
    -0.35
    POSITIVE LOGITS
     surrounded
    0.91
     awaiting
    0.87
     waiting
    0.78
     listening
    0.68
     enjoying
    0.66
     watching
    0.66
     ready
    0.65
     doing
    0.64
     rodeado
    0.63
     sipping
    0.62
    Activations Density 0.547%

    No Known Activations