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. 0-GEMMASCOPE-RES-16K
    6. 6771
    Prev
    Next
    INDEX
    Explanations

    patterns of punctuation and formatting, particularly relating to the structure of headings and lists in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %")
    -0.58
     ๆ
    -0.58
    "):
    
    -0.57
    migrationBuilder
    -0.56
    ")]
    
    -0.55
    FontOfSize
    -0.52
     تط
    -0.51
    CALLBACK
    -0.50
    %");
    -0.50
    hdysval
    -0.50
    POSITIVE LOGITS
     ה
    0.82
     כשה
    0.76
    sizeCache
    0.76
     מה
    0.75
    最快更新
    0.72
     כ
    0.72
     ['./
    0.70
    ανα
    0.70
     genoux
    0.68
     scurt
    0.68
    Activations Density 0.195%

    No Known Activations