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. 20-GEMMASCOPE-RES-16K
    6. 1144
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical functions, specifically those involving greatest common divisors and factors

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

    "common divisor" or "common factor" calculations

    np_acts-logits-general · gemini-2.0-flash

    greatest common divisor or factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.54
    下载附件
    -0.54
     صوتيه
    -0.53
     BytesLike
    -0.52
    httphttps
    -0.52
    RenderAtEndOf
    -0.46
     NSCoder
    -0.44
    saraba
    -0.44
     referenties
    -0.43
     Lengkap
    -0.43
    POSITIVE LOGITS
    цездатний
    0.59
    transQ
    0.46
    mybatisplus
    0.43
    InsertCommand
    0.40
     AssemblyCulture
    0.38
     Савезне
    0.37
    autorest
    0.37
     OMITBAD
    0.37
    PCell
    0.36
    libft
    0.36
    Activations Density 1.027%

    No Known Activations