© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 29109
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to parts or portions of a whole

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

    portion and portions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    <bos>
    -0.79
    Autoritní
    -0.66
     NavController
    -0.60
    RTLD
    -0.59
    ⓧ
    -0.54
    AndEndTag
    -0.53
    steering
    -0.51
    Contactez
    -0.51
     juges
    -0.51
     scolaires
    -0.50
    POSITIVE LOGITS
     portion
    1.23
     Portion
    1.16
    portion
    1.12
    Portion
    1.11
     portions
    1.02
     Portions
    0.88
     porción
    0.85
     Section
    0.73
    部分
    0.71
     gedeelte
    0.71
    Activations Density 0.013%

    No Known Activations