Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6588
    Prev
    Next
    INDEX
    Explanations

    structured elements, such as matrices and formatted mathematical expressions

    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
     himo
    -0.63
    balleur
    -0.61
     AspNetCore
    -0.59
     tartalomajánló
    -0.58
    цездатний
    -0.57
    opsida
    -0.56
    Наводи
    -0.55
    transQ
    -0.53
    hamshire
    -0.52
    >−
    -0.52
    POSITIVE LOGITS
     NSCoder
    0.85
     defaultstate
    0.84
    VersionUID
    0.75
    WebVitals
    0.72
    StoreMessageInfo
    0.70
    Autoritní
    0.69
     ویکی‌پدیا
    0.65
    RefNanny
    0.62
    sidemargin
    0.61
    bootstrapcdn
    0.59
    Activations Density 0.027%

    No Known Activations