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. 2074
    Prev
    Next
    INDEX
    Explanations

    numbers represented in decimal format within a certain range

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

    Code, math, or uncommon characters

    np_acts-logits-general · gemini-2.0-flash

    technical terms and programming concepts

    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
    Enllaces
    -0.52
    TabStop
    -0.49
    new
    -0.47
     "
    -0.47
    ama
    -0.47
    faßt
    -0.46
     pemimpin
    -0.44
     new
    -0.44
     '
    -0.44
    Herkunft
    -0.43
    POSITIVE LOGITS
    DockStyle
    1.08
    ⓧ
    1.04
    Datuak
    1.00
    findpost
    0.90
    MigrationBuilder
    0.87
     EconPapers
    0.85
     houſe
    0.83
    IsContent
    0.82
     Houſe
    0.81
    migrationBuilder
    0.79
    Activations Density 0.079%

    No Known Activations