© 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. 1430
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to liability and actions in software agreements

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

    legal terminology and references to legal documents and proceedings.

    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
    Runnable
    -0.31
     рабочего
    -0.27
     leaders
    -0.27
     loyal
    -0.27
    PlayerPrefs
    -0.27
     рабочих
    -0.26
     working
    -0.26
     rep
    -0.25
     realise
    -0.25
    ,
    -0.25
    POSITIVE LOGITS
    AccessorTable
    1.43
     виправивши
    1.26
    UseVisualStyle
    1.24
     NSCoder
    1.23
    parsedMessage
    1.12
    IndentedString
    1.09
    MessageTagHelper
    1.08
    WriteBarrier
    1.07
     getItemCount
    1.07
    setVerticalGroup
    1.07
    Activations Density 0.358%

    No Known Activations