© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4146
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and methodology

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

    legal and bureaucratic terminology related to official documents and processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    formal professional or legal language related to documents, trials, or academic research.

    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
     CreateTagHelper
    -0.62
    ModelSerializer
    -0.55
    charCodeAt
    -0.50
    sendFile
    -0.47
    peo
    -0.46
    GEBURTSDATUM
    -0.45
    enio
    -0.45
    økt
    -0.45
    omla
    -0.44
    entas
    -0.43
    POSITIVE LOGITS
    ьажоргаш
    0.57
     Winaray
    0.44
    AutoModerator
    0.43
     faſt
    0.43
     Taktlose
    0.42
    -------------</
    0.40
     հղումներ
    0.39
     purpoſe
    0.39
    Cyfeiriadau
    0.38
     Anſ
    0.38
    Activations Density 1.497%

    No Known Activations