© 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. 8-GEMMASCOPE-RES-16K
    11. 6765
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize experimentation and sampling different options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entretien
    -0.31
     pungkasnya
    -0.30
     jūs
    -0.26
    DBObject
    -0.26
     afspraak
    -0.25
     säll
    -0.25
     tor
    -0.25
    payments
    -0.24
     hjär
    -0.24
     navnet
    -0.24
    POSITIVE LOGITS
     tested
    1.02
     Tested
    1.02
    Tested
    1.00
     trial
    0.91
     Tried
    0.89
     Trial
    0.89
     testing
    0.89
    tested
    0.86
    Trial
    0.85
     TRIAL
    0.85
    Activations Density 0.197%

    No Known Activations