© 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. 39-GEMMASCOPE-RES-16K
    6. 2740
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of individuals and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schlag
    -0.33
    ứ
    -0.33
     croce
    -0.33
    cheid
    -0.32
    はず
    -0.31
    бы
    -0.31
    ')")
    -0.30
     пи
    -0.30
    coated
    -0.29
    way
    -0.29
    POSITIVE LOGITS
     interested
    0.91
     considering
    0.82
     thinking
    0.77
     wondering
    0.77
     unsure
    0.76
     planning
    0.75
     unfamiliar
    0.75
     serious
    0.72
    interested
    0.71
     feeling
    0.71
    Activations Density 0.217%

    No Known Activations