© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11468
    Prev
    Next
    INDEX
    Explanations

    references to numerical codes or identifiers typically seen in technical or structured data contexts

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

    UUID-like hexadecimal strings

    np_acts-logits-general · gemini-2.0-flash

    guid identifiers

    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
    RegistryLite
    -0.61
    httphttps
    -0.59
     createState
    -0.59
     chaleco
    -0.54
    ことなく
    -0.54
     wedi
    -0.52
    sendRedirect
    -0.50
     actually
    -0.50
    actually
    -0.48
     Réponses
    -0.48
    POSITIVE LOGITS
    orteur
    0.56
    amique
    0.54
    Chorus
    0.53
    abestanden
    0.50
    Refrain
    0.50
    casm
    0.48
    RNG
    0.47
    maphore
    0.47
     defStyleAttr
    0.47
    ільки
    0.47
    Activations Density 0.220%

    No Known Activations