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. 15712
    Prev
    Next
    INDEX
    Explanations

    structures and elements related to PHP and Laravel programming

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

    PHP, Javascript, or Laravel code snippets

    np_acts-logits-general · gemini-2.0-flash

    Laravel and framework code

    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
     autorytatywna
    -0.44
    出版年
    -0.43
     disambiguazione
    -0.42
    SourceChecksum
    -0.41
     مرئيه
    -0.41
    Espèce
    -0.40
     насељу
    -0.38
     retired
    -0.37
    ButtonStyle
    -0.37
     cellspacing
    -0.36
    POSITIVE LOGITS
     Laravel
    0.52
    tagHelper
    0.50
     Juga
    0.48
    thylamine
    0.47
    conia
    0.46
    ❦
    0.45
     himo
    0.44
    mybatisplus
    0.44
     Iggy
    0.44
    AccessorTable
    0.44
    Activations Density 0.029%

    No Known Activations