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. 21-GEMMASCOPE-RES-16K
    6. 7539
    Prev
    Next
    INDEX
    Explanations

    phrases related to laboratory procedures involving liquids and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yyr
    -0.52
     Friedhof
    -0.50
    itemBuilder
    -0.50
    +#+#
    -0.50
    tudiant
    -0.50
    astify
    -0.47
     XCTest
    -0.46
    phalt
    -0.43
     recev
    -0.43
     Moura
    -0.43
    POSITIVE LOGITS
     water
    2.30
    water
    1.87
    Water
    1.79
     Water
    1.76
     WATER
    1.74
     agua
    1.61
    WATER
    1.60
     waters
    1.57
     água
    1.50
     Wasser
    1.39
    Activations Density 0.279%

    No Known Activations