© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 106774
    Prev
    Next
    INDEX
    Explanations

    references to "free" in various contexts, indicating a focus on freedom or freedom-related concepts

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

    "free" followed by concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hematics
    -0.54
     Chapters
    -0.52
    bootstrapcdn
    -0.50
     Discogs
    -0.49
    onson
    -0.48
     cioccolato
    -0.47
     Chapter
    -0.47
     NPD
    -0.47
    ations
    -0.46
     UserRepository
    -0.46
    POSITIVE LOGITS
     free
    1.98
    Free
    1.95
     Free
    1.88
    free
    1.85
    FREE
    1.59
     FREE
    1.55
     libre
    1.26
     freie
    1.18
     freien
    1.18
     frees
    1.17
    Activations Density 0.025%

    No Known Activations