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. 5-GEMMASCOPE-RES-16K
    6. 2066
    Prev
    Next
    INDEX
    Explanations

    certain syntactic or structural elements in code, particularly those related to function definitions or calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.98
     незавершена
    -0.88
     فريبيس
    -0.80
     EconPapers
    -0.80
    ngdoc
    -0.79
     fieldNum
    -0.79
    saraba
    -0.77
    findpost
    -0.74
    ReusableCell
    -0.73
    endmodule
    -0.73
    POSITIVE LOGITS
    (
    0.91
    ("(
    0.68
    ">(
    0.61
    ">(</
    0.61
    >(</
    0.60
    {(
    0.56
     “(
    0.56
    ((
    0.56
    })(
    0.56
      (
    0.53
    Activations Density 0.178%

    No Known Activations