© 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. 3762
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and naming conventions, particularly in the context of coding practices and software development

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

    technical or scientific discussions about measurement, statistical properties, and quantitative descriptions.

    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
     Meksiku
    -0.51
    #+#
    -0.43
     MB
    -0.38
    ђу
    -0.35
     note
    -0.34
    APIView
    -0.34
     MIS
    -0.33
     notes
    -0.33
     Thus
    -0.33
     M
    -0.32
    POSITIVE LOGITS
    ſelves
    0.63
     myſelf
    0.62
     كومونز
    0.60
     leaſt
    0.60
     Monfieur
    0.60
     becauſe
    0.57
    wiſe
    0.57
     itſelf
    0.56
     raiſ
    0.55
     uſed
    0.55
    Activations Density 0.412%

    No Known Activations