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. 2881
    Prev
    Next
    INDEX
    Explanations

    information related to memorial services and their details

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

    Mathematical or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    numerical and symbolic expressions

    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
    CppCodeGen
    -0.60
     lenker
    -0.56
    מד
    -0.55
    stateProvider
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    +#+#
    -0.54
     clés
    -0.53
     nahilalakip
    -0.51
     légiti
    -0.49
    żar
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.70
     donations
    0.66
     mourners
    0.64
    Distribuzione
    0.62
     visitation
    0.61
    ModelBuilder
    0.61
    đồ
    0.61
     family
    0.60
     RSVP
    0.60
     friends
    0.59
    Activations Density 0.011%

    No Known Activations