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. 20-GEMMASCOPE-RES-16K
    6. 1224
    Prev
    Next
    INDEX
    Explanations

    references to arrays in programming or data structures

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

    "array" or "Array"

    np_acts-logits-general · gemini-2.0-flash

    array data structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    italic
    -0.51
    ‴
    -0.48
     ویکی‌پدی
    -0.48
     xlink
    -0.48
    contentLoaded
    -0.47
    Cen
    -0.46
    lime
    -0.45
    }^\
    -0.45
    Vic
    -0.44
     فريبيس
    -0.43
    POSITIVE LOGITS
     Array
    1.30
    Array
    1.28
     array
    1.27
    array
    1.23
    ARRAY
    1.09
     Arrays
    1.06
     arrays
    1.05
     ARRAY
    1.02
    Arrays
    1.02
    数组
    0.89
    Activations Density 0.179%

    No Known Activations