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. 15587
    Prev
    Next
    INDEX
    Explanations

    technical syntax and structure in programming or technical documents

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

    Tokens after "<" in code

    np_acts-logits-general · gemini-2.0-flash

    programming generics, types, and structures

    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
     Ее
    -0.40
     useSelector
    -0.35
     Isso
    -0.34
    这才
    -0.33
     passage
    -0.32
     كمان
    -0.32
     Übers
    -0.32
     klart
    -0.31
     ""],
    -0.30
     будешь
    -0.30
    POSITIVE LOGITS
     مرئيه
    0.69
     itſelf
    0.63
     AssemblyTitle
    0.62
     arşivlendi
    0.61
    Vidite
    0.60
     CreateTagHelper
    0.59
     ویکی‌پدی
    0.59
    oredCriteria
    0.56
    antMatchers
    0.56
    thenReturn
    0.53
    Activations Density 0.179%

    No Known Activations