© 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. 7818
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data encoding and decoding processes

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

    references to binary data types like 'bytes' and 'buffer' in programming code.

    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
     XCTest
    -0.41
     McCra
    -0.38
     SDLK
    -0.37
     increí
    -0.34
     Stewart
    -0.34
     Foster
    -0.34
    #+#
    -0.33
     conced
    -0.33
     manifiesto
    -0.33
     ganchillo
    -0.32
    POSITIVE LOGITS
    ioutil
    0.68
     bytes
    0.68
    bytes
    0.67
    Bytes
    0.66
    byte
    0.66
     Bytes
    0.66
    AccessFile
    0.66
     byte
    0.65
    
    0.62
    rawDesc
    0.61
    Activations Density 0.352%

    No Known Activations