© 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. 39-GEMMASCOPE-RES-16K
    11. 2907
    Prev
    Next
    INDEX
    Explanations

    references to freedom of speech and expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.52
    setVerticalGroup
    -0.50
    ⌄
    -0.49
    ndice
    -0.49
    Hentet
    -0.48
     looped
    -0.46
     AssemblyCompany
    -0.45
     familières
    -0.45
    Nacional
    -0.45
    borderFill
    -0.44
    POSITIVE LOGITS
     freedom
    1.92
    freedom
    1.62
     Freedom
    1.56
    Freedom
    1.52
     freedoms
    1.46
     liberty
    1.38
     FREEDOM
    1.37
     libertà
    1.34
     libertad
    1.32
     liberté
    1.29
    Activations Density 0.779%

    No Known Activations