© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5429
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking away rights or property

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

    Confiscation, seizure, or taking away

    np_acts-logits-general · gemini-2.0-flash

    taking property or rights

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    bootstrapcdn
    -0.49
    Trọng
    -0.46
    glLoad
    -0.45
     relâche
    -0.42
    cheiben
    -0.42
     Exteriores
    -0.40
    tré
    -0.40
    
    -0.37
    Referanser
    -0.37
    Normalize
    -0.37
    POSITIVE LOGITS
     snatch
    0.75
     seizure
    0.75
     steals
    0.70
     seized
    0.70
     seizing
    0.70
     confiscated
    0.67
     snatched
    0.66
     seize
    0.66
     stolen
    0.66
     confis
    0.66
    Activations Density 0.592%

    No Known Activations