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. 4335
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to recursive formulas or equations

    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
     “
    -0.56
     ‘
    -0.55
    者に
    -0.52
    Portail
    -0.51
    rasti
    -0.50
     vers
    -0.48
    ,
    -0.48
     of
    -0.48
     y
    -0.48
     trai
    -0.47
    POSITIVE LOGITS
     GenerationType
    1.03
     getItemId
    0.95
     المعيارى
    0.95
     للمعارف
    0.90
    enumi
    0.87
     AssemblyCulture
    0.87
    ंदीखरीदारी
    0.85
     متعلقه
    0.85
     betweenstory
    0.84
     Audiodateien
    0.84
    Activations Density 0.781%

    No Known Activations