© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 12227
    Prev
    Next
    INDEX
    Explanations

    occurrences of the variable "i" in a programming context, particularly in loops or indexing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.81
    verifyException
    -0.66
    IVEREF
    -0.66
    writeFieldEnd
    -0.66
    TagMode
    -0.64
    цездатний
    -0.64
     snippetHide
    -0.63
    ьаж
    -0.62
     مرئيه
    -0.62
     незавершена
    -0.60
    POSITIVE LOGITS
    ++)
    0.50
    ++
    0.36
     +=
    0.35
     Técnico
    0.35
     faite
    0.34
     Collaboration
    0.33
    utuhkan
    0.32
     Leggings
    0.32
     fallait
    0.31
     fijo
    0.31
    Activations Density 0.041%

    No Known Activations