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. 11-GEMMASCOPE-RES-16K
    6. 5820
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures related to resource management and handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.80
     متعلقه
    -0.76
    dersfield
    -0.74
    __':
    -0.73
     tartalomajánló
    -0.70
    detectChanges
    -0.64
    UpInside
    -0.62
    gucigalpa
    -0.61
    #+#
    -0.57
    الدراسه
    -0.57
    POSITIVE LOGITS
    useEffect
    0.71
     kasarigan
    0.67
    TagMode
    0.66
    makeText
    0.63
    BeginContext
    0.62
     ویکی‌پدی
    0.61
     lenker
    0.61
    منابع
    0.60
    iyor
    0.58
     חיצוניים
    0.58
    Activations Density 0.328%

    No Known Activations