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. 32
    Prev
    Next
    INDEX
    Explanations

    closing XML/HTML tags and closing brackets/braces, particularly at the end of code blocks or structures.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    XML or HTML-like tag structures and their attributes

    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
     otomatig
    -0.71
     propOrder
    -0.67
     ویکی‌پدی
    -0.64
    TagMode
    -0.59
    principalTable
    -0.59
     Réponses
    -0.56
    SharedCtor
    -0.55
    ↹
    -0.54
     المعيارى
    -0.54
    setVerticalGroup
    -0.52
    POSITIVE LOGITS
     AssemblyProduct
    0.44
    chenden
    0.39
    rø
    0.38
    insegna
    0.38
    Lunes
    0.37
    PerformLayout
    0.36
     kirj
    0.36
    ควร
    0.36
    argli
    0.36
     compagn
    0.36
    Activations Density 0.570%

    No Known Activations