© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1735
    Prev
    Next
    INDEX
    Explanations

    instances of programming or coding-related structures in the document

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

    Code snippets with "cur" and "idx"

    np_acts-logits-general · gemini-2.0-flash

    cur: followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     disambiguazione
    -0.77
     للاسماء
    -0.73
    Diweddarwch
    -0.71
     ujednoznacz
    -0.69
    GEBURTSDATUM
    -0.68
     дописавши
    -0.67
    parsedMessage
    -0.61
     Normdatei
    -0.60
    KURZBESCHREIBUNG
    -0.60
     estekak
    -0.59
    POSITIVE LOGITS
     Moulton
    0.38
     lei
    0.38
    miyorum
    0.37
    ouk
    0.37
     Lei
    0.36
     also
    0.35
    ður
    0.35
    neil
    0.35
    Lei
    0.35
    dou
    0.34
    Activations Density 0.463%

    No Known Activations