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. 15599
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software implementation and protocol definitions

    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
    ButtonModule
    -0.50
    ,
    -0.47
    glGet
    -0.47
    zorg
    -0.45
    IGraphics
    -0.44
    onResume
    -0.43
     requestCode
    -0.43
    oprecipitation
    -0.42
    QtCore
    -0.42
    bundet
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.73
     snippetHide
    0.64
    )++;
    0.64
    المشاركات
    0.57
     مرئيه
    0.56
    脚注の使い方
    0.56
    ("")]
    
    0.56
    ้อมูล
    0.55
    互联网档案馆
    0.55
    ]--;
    0.54
    Activations Density 0.356%

    No Known Activations