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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10605
    Prev
    Next
    INDEX
    Explanations

    function definitions and their initializations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.79
    LookAnd
    -0.76
    よいよ
    -0.70
     öffnungszeiten
    -0.69
    ?}",
    -0.66
    ",&
    -0.65
    memcmp
    -0.63
    ">',
    -0.61
    {}",
    -0.61
     =",
    -0.61
    POSITIVE LOGITS
    __(
    0.97
     مشين
    0.74
    ReusableCell
    0.72
    MemoryWarning
    0.69
    KommentareTeilen
    0.69
    ագրություններ
    0.67
    Sprintf
    0.65
    θρω
    0.65
     StatelessWidget
    0.64
     gainera
    0.63
    Activations Density 0.036%

    No Known Activations