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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13415
    Prev
    Next
    INDEX
    Explanations

    references to biological structures and processes

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

    "Bi" and similar terms (e.g., "bi-", "biphasic", "bipartite")

    np_acts-logits-general · gemini-2.0-flash

    bi- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.98
     <<<<<<<<<<<<<<
    -0.95
    InputBorder
    -0.86
    MessageOf
    -0.80
    ImageContext
    -0.80
    UserScript
    -0.79
    ContentLoaded
    -0.78
    ;->
    -0.76
    UnusedPrivate
    -0.75
     houſe
    -0.71
    POSITIVE LOGITS
     bi
    0.80
     Bi
    0.75
     Bid
    0.62
    Бі
    0.62
     Би
    0.62
     बि
    0.61
     Bir
    0.61
     bir
    0.61
    Bi
    0.60
    Bid
    0.59
    Activations Density 0.195%

    No Known Activations