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. 7486
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements used in programming languages

    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
    tvguidetime
    -0.66
    tagHelperRunner
    -0.62
    mybatisplus
    -0.56
    AsUp
    -0.54
    Clik
    -0.52
    WaitGroup
    -0.52
     كومونز
    -0.51
     SwitchCompat
    -0.51
    ekse
    -0.50
     curiosity
    -0.49
    POSITIVE LOGITS
     translations
    1.21
     translation
    1.18
     localize
    1.17
     localization
    1.16
     localized
    1.15
     translators
    1.13
     Localized
    1.09
     translated
    1.08
     translate
    1.08
     Localization
    1.07
    Activations Density 0.464%

    No Known Activations