© 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. 24-GEMMASCOPE-RES-16K
    6. 14598
    Prev
    Next
    INDEX
    Explanations

    references to binding affinities in biochemical contexts

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

    "Binding" or "bound" tokens

    np_acts-logits-general · gemini-2.0-flash

    direct binding target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    serviceWorker
    -0.52
     villagers
    -0.48
     paille
    -0.48
     villages
    -0.47
     Stroh
    -0.46
     пен
    -0.46
     Dorf
    -0.46
     hamlet
    -0.46
    vektor
    -0.46
     Serrano
    -0.45
    POSITIVE LOGITS
     binding
    3.52
     bind
    3.40
     Binding
    3.22
     bound
    3.20
     Bind
    3.11
     binds
    3.04
     BIND
    3.00
    binding
    2.99
    Binding
    2.91
    bind
    2.90
    Activations Density 0.352%

    No Known Activations