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. 15971
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data storage structures

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

    Code, equations, and commands

    np_acts-logits-general · gemini-2.0-flash

    user queries related to classifiers

    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
    請繼續往下閱讀
    -0.42
    帖最后由
    -0.41
     صوتيه
    -0.40
    KommentareTeilen
    -0.40
    msgTypes
    -0.39
    MLLoader
    -0.38
    ="#"><
    -0.37
     فريبيس
    -0.35
    icolo
    -0.34
    numerusform
    -0.34
    POSITIVE LOGITS
     **
    1.13
    (**
    0.98
    **
    0.97
    ,**
    0.91
    **(
    0.77
    **,
    0.74
    **)
    0.70
    .**
    0.70
    **.
    0.67
     **)
    0.65
    Activations Density 0.117%

    No Known Activations