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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11154
    Prev
    Next
    INDEX
    Explanations

    variations of the term "init" used in class definitions and method declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.02
     snippetHide
    -1.01
    AddTagHelper
    -0.95
    MigrationBuilder
    -0.92
    ParallelGroup
    -0.83
    AndEndTag
    -0.79
     lenker
    -0.79
     елның
    -0.74
     typelib
    -0.73
    )";
    
    -0.73
    POSITIVE LOGITS
    NonNull
    1.52
    AutoSize
    0.83
    init
    0.80
    Nonnull
    0.73
    NotNull
    0.66
    construct
    0.63
     daim
    0.62
     nhiêu
    0.57
     Stateless
    0.57
    آباد
    0.54
    Activations Density 0.024%

    No Known Activations