© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10699
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and affiliations in scientific contexts

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

    Names followed by publication information

    np_acts-logits-general · gemini-2.0-flash

    names followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.72
    principalColumn
    -0.66
    Diweddarwch
    -0.64
     autorytatywna
    -0.57
    httphttps
    -0.57
     înc
    -0.56
    UrlResolution
    -0.56
    MigrationBuilder
    -0.56
    GHIJKLM
    -0.55
    tvguidetime
    -0.55
    POSITIVE LOGITS
     Inflammation
    0.40
    évaluateur
    0.39
    hoben
    0.38
    ницы
    0.36
    updateUI
    0.36
     Cells
    0.35
    ERRORS
    0.35
    zogen
    0.34
    .
    0.34
     II
    0.34
    Activations Density 0.658%

    No Known Activations