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
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 389
    Prev
    Next
    INDEX
    Explanations

    syntactic elements and definitions related to coding structures, particularly in Python and C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.74
    IntoConstraints
    -0.66
    RetentionPolicy
    -0.65
    ftagPool
    -0.62
    IUrlHelper
    -0.61
    WebMethod
    -0.57
    tagHelperRunner
    -0.57
     AssemblyCompany
    -0.56
    InjectAttribute
    -0.56
    stateProvider
    -0.55
    POSITIVE LOGITS
    internal
    0.74
     internal
    0.62
    Internal
    0.60
     Internal
    0.60
     internally
    0.51
    Pyx
    0.51
    INTERNAL
    0.49
     Exacts
    0.48
    内部
    0.47
     wewnętr
    0.45
    Activations Density 0.273%

    No Known Activations