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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15583
    Prev
    Next
    INDEX
    Explanations

    words related to opportunities and challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions like "for" and words associated with it

    np_acts-logits-general · gemini-2.0-flash

    prepositions indicating purpose or recipient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.57
     تضيفلها
    -0.56
    Попис
    -0.49
    postIndex
    -0.48
     NSCoder
    -0.48
    MigrationBuilder
    -0.45
     Administrativna
    -0.45
    扨
    -0.44
    getMenuInflater
    -0.44
     CreateTagHelper
    -0.43
    POSITIVE LOGITS
     for
    1.63
     bagi
    1.59
     dla
    1.38
     для
    1.34
     עבור
    1.30
     für
    1.15
     بالنسبة
    1.15
    สำหรับ
    1.13
    对于
    1.05
     Bagi
    1.05
    Activations Density 0.936%

    No Known Activations