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. 15966
    Prev
    Next
    INDEX
    Explanations

    instances of the term "include" as it relates to code libraries or modules in programming

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

    C/C++ include statements

    np_acts-logits-general · gemini-2.0-flash

    #include directives

    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
    transQ
    -0.48
    RegressionTest
    -0.45
    RTCF
    -0.44
    省市镇
    -0.41
     BoxFit
    -0.40
    careous
    -0.39
     Misses
    -0.38
    ❹
    -0.37
    يكب
    -0.37
    pointments
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.73
     nahilalakip
    0.66
    BeginInit
    0.54
    hyrchwyd
    0.54
    Билгалдахарш
    0.48
     CreateTagHelper
    0.46
    المشاركات
    0.44
    .*")]
    0.43
    ########.
    0.42
    Identyfik
    0.41
    Activations Density 0.030%

    No Known Activations