© 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. 9021
    Prev
    Next
    INDEX
    Explanations

    specific terms related to electronic components and their applications

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

    examples of technology applications and use cases across various industries.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    djangoproject
    -0.38
     AssemblyTitle
    -0.36
     Umum
    -0.34
    ✥
    -0.33
     Cárdenas
    -0.31
    ęki
    -0.30
    LEncoder
    -0.30
     ked
    -0.29
     naman
    -0.28
     godt
    -0.28
    POSITIVE LOGITS
    MENAFN
    0.61
     airports
    0.57
    leſs
    0.56
     sculptors
    0.56
     poets
    0.55
     leſs
    0.54
     autorytatywna
    0.53
    ſelves
    0.53
     Anſ
    0.53
    RTEE
    0.52
    Activations Density 0.532%

    No Known Activations