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. 16-GEMMASCOPE-RES-16K
    6. 12614
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the depth or extent of investigation and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding verbs/adverbs ending in "-ly"

    np_acts-logits-general · gemini-2.0-flash

    adverbs of degree or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.48
    __':
    -0.45
    avl
    -0.45
    werf
    -0.43
    specifier
    -0.43
     vân
    -0.43
     transferable
    -0.43
    学位
    -0.42
    arque
    -0.42
    λαμβ
    -0.42
    POSITIVE LOGITS
     nakalista
    0.80
     מאוד
    0.72
    RegressionTest
    0.69
    Izvori
    0.61
    OrBuilder
    0.61
     disambiguazione
    0.59
    StoreMessageInfo
    0.58
    +#+#
    0.57
     ujednoznacz
    0.56
    hamcrest
    0.55
    Activations Density 0.370%

    No Known Activations