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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15508
    Prev
    Next
    INDEX
    Explanations

    indicators of emphasis or significance in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.71
    EDEFAULT
    -0.65
     kasarigan
    -0.63
     Савезне
    -0.62
    données
    -0.61
     nhàng
    -0.60
    CustomAttributes
    -0.60
    曖昧さ回避
    -0.57
    IUrlHelper
    -0.57
     चुनें
    -0.56
    POSITIVE LOGITS
    retum
    0.57
    forChild
    0.56
    esModule
    0.53
    </blockquote>
    0.50
    CppMethod
    0.49
     larmes
    0.49
    ("")]
    
    0.47
    اسی
    0.46
    findpost
    0.46
    abha
    0.45
    Activations Density 0.003%

    No Known Activations