Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16069
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to treatments and drugs

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

    "Squ" or "Aqu" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    squ|sequoia|aquaporin|sqw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.69
    MLLoader
    -0.68
    SourceChecksum
    -0.55
    GOTREF
    -0.54
    ">//
    -0.54
    Derbyniad
    -0.52
    isContained
    -0.52
    sizeCache
    -0.51
    parsedMessage
    -0.51
    httphttps
    -0.50
    POSITIVE LOGITS
     Squ
    0.86
     squ
    0.73
    Squ
    0.71
    squ
    0.63
     SQ
    0.60
     SQU
    0.57
     Sq
    0.55
     sq
    0.54
    Equ
    0.53
    Aqu
    0.52
    Activations Density 0.229%

    No Known Activations