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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53797
    Prev
    Next
    INDEX
    Explanations

    declarations of types in programming, specifically those using the `typedef` keyword

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    pulumi
    -0.54
    horabuena
    -0.52
    SqlClient
    -0.51
     immobilier
    -0.49
     corrupción
    -0.47
    braucher
    -0.47
    HomeComponent
    -0.46
    liesslich
    -0.46
    AppComponent
    -0.46
     devriez
    -0.45
    POSITIVE LOGITS
    typedef
    1.73
     typedef
    1.12
     tartalomajánló
    0.59
    RegisterType
    0.58
     AssemblyTitle
    0.56
    complexType
    0.56
    DOCTYPE
    0.54
     وتسجيلات
    0.53
    TypeId
    0.50
    DIPSETTING
    0.50
    Activations Density 0.004%

    No Known Activations