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. 20-GEMMASCOPE-RES-16K
    6. 66
    Prev
    Next
    INDEX
    Explanations

    patterns related to statistical or numerical data

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

    complex numerical or computational representations with multiple values separated by commas.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Хьажоргаш
    -0.66
    rungsseite
    -0.61
    Билгалдахарш
    -0.60
    存于互联网档案馆
    -0.58
     חיצוניים
    -0.57
    pulumi
    -0.55
    AddTagHelper
    -0.54
     ویکی‌پدیا
    -0.54
    újo
    -0.54
    ReusableCell
    -0.53
    POSITIVE LOGITS
     MotionEvent
    0.34
    lorette
    0.34
     together
    0.32
    maior
    0.32
     typelib
    0.32
    性的
    0.32
     通販
    0.31
    บ้าง
    0.31
    roja
    0.30
    tan
    0.30
    Activations Density 0.549%

    No Known Activations