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. 20-GEMMASCOPE-RES-16K
    6. 6423
    Prev
    Next
    INDEX
    Explanations

    quantitative measures or statistics related to agriculture and environmental resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ليب
    -0.50
    ))))
    -0.47
     although
    -0.46
     graines
    -0.45
    ))),
    -0.44
     elsewhere
    -0.43
    кож
    -0.42
     connaissances
    -0.42
    ↵↵
    -0.41
    了下去
    -0.41
    POSITIVE LOGITS
     thousand
    1.18
     million
    1.12
    TestingModule
    1.08
     hundred
    1.04
    thousand
    0.99
     thousands
    0.97
     billion
    0.96
     THOUS
    0.94
     millions
    0.92
    thousands
    0.90
    Activations Density 0.322%

    No Known Activations