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. 4546
    Prev
    Next
    INDEX
    Explanations

    patterns and structures commonly used in mathematical equations and matrix representations

    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
     ويكيميديا
    -0.74
    ();)
    -0.72
     tartalomajánló
    -0.70
    MemoryWarning
    -0.69
     vapours
    -0.67
     unmute
    -0.65
     vapors
    -0.64
    APORE
    -0.64
     Autorizaciones
    -0.63
    Melhor
    -0.63
    POSITIVE LOGITS
    SizeMode
    0.52
    Personendaten
    0.50
     وتسجيلات
    0.47
     noqa
    0.45
    BagLayout
    0.44
     drive
    0.41
    ]='\
    0.41
    kloped
    0.38
     R
    0.38
    Observable
    0.38
    Activations Density 0.426%

    No Known Activations