© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 11432
    Prev
    Next
    INDEX
    Explanations

    keywords associated with capture, imprisonment, and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niająca
    -0.55
    ően
    -0.50
     SMART
    -0.50
    ="@+
    -0.47
    atisfied
    -0.46
    atoon
    -0.45
     propOrder
    -0.45
    ้อ
    -0.44
    etration
    -0.44
     strukt
    -0.44
    POSITIVE LOGITS
     transported
    0.64
     handcu
    0.61
     newOwner
    0.61
     transport
    0.59
    UpInside
    0.58
    ')}}"
    0.57
    uxxxx
    0.57
     транспорти
    0.56
     dibawa
    0.56
     handcuffs
    0.56
    Activations Density 0.464%

    No Known Activations