© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1917
    Prev
    Next
    INDEX
    Explanations

    actions and conditions related to obligations or responsibilities

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

    verbs and auxiliary verbs like "be", "do", and "can".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     gyhoeddwyd
    -0.79
    iffance
    -0.76
     Вікі
    -0.75
    transQ
    -0.73
    Identyfik
    -0.71
    iſen
    -0.70
    tiérrez
    -0.69
     ſeinen
    -0.69
    mybatisplus
    -0.69
    itsubishi
    -0.68
    POSITIVE LOGITS
     extérieure
    0.34
     Keuangan
    0.31
     extérieurs
    0.30
     quelconque
    0.29
     polaire
    0.29
    venidos
    0.29
     Lingkungan
    0.28
     πως
    0.28
    <em>
    0.28
    Clik
    0.28
    Activations Density 0.546%

    No Known Activations