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. 4597
    Prev
    Next
    INDEX
    Explanations

    references to numerical measurements and units

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

    Preceding ordinal numbers or parts of a whole

    np_acts-logits-general · gemini-2.0-flash

    quantifier noun sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Week
    -0.54
     Woche
    -0.52
    middag
    -0.51
     week
    -0.51
    ListItemIcon
    -0.49
     Day
    -0.48
     No
    -0.45
    terday
    -0.45
    Durée
    -0.44
    Week
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.93
    fjspx
    0.87
     bezeichneter
    0.84
    SharedDtor
    0.82
    (!__
    0.72
    providedIn
    0.71
     Савезне
    0.69
    annica
    0.69
    erialization
    0.68
    Gön
    0.68
    Activations Density 0.349%

    No Known Activations