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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102329
    Prev
    Next
    INDEX
    Explanations

    tokens and abbreviations related to technical specifications

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

    French language text fragments containing common French language elements like contractions (d', qu', l'), accented characters (é, è, à), punctuation patterns, and French words/phrases, often appearing in chat or code contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Roskov
    -0.57
     незавершена
    -0.51
    NameInMap
    -0.47
     ornament
    -0.44
    StructEnd
    -0.42
     ویکی‌پدی
    -0.42
    #+#
    -0.41
     honor
    -0.41
    Controllo
    -0.38
    testify
    -0.38
    POSITIVE LOGITS
    ">//
    0.54
    httphttps
    0.47
    érat
    0.43
    Harper
    0.43
    zepte
    0.43
     Mendez
    0.41
     governments
    0.41
     BoxFit
    0.41
     natür
    0.40
    ドウ
    0.40
    Activations Density 0.066%

    No Known Activations