© 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. 12573
    Prev
    Next
    INDEX
    Explanations

    references to vehicle specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    -0.34
     scolas
    -0.34
     umana
    -0.34
    новниш
    -0.34
    Ằ
    -0.33
    ğraf
    -0.32
     referrerpolicy
    -0.31
    ::$_
    -0.31
    uisine
    -0.30
     pommes
    -0.30
    POSITIVE LOGITS
    ޸
    0.53
    AndEndTag
    0.53
    ArgumentParser
    0.52
    อย่างไร
    0.47
     CLS
    0.47
    liner
    0.46
     Tivoli
    0.46
     lenker
    0.45
    lisis
    0.45
    Buster
    0.45
    Activations Density 0.446%

    No Known Activations