© 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. 30-GEMMASCOPE-RES-16K
    11. 10779
    Prev
    Next
    INDEX
    Explanations

    terms related to local governance and administrative roles

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

    Followed by specific locations/names

    np_acts-logits-general · gemini-2.0-flash

    Lancaster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.49
    UniformLocation
    -0.44
    SystemColors
    -0.44
     Sjö
    -0.40
     Lindberg
    -0.39
     howl
    -0.38
     Zem
    -0.37
     Australian
    -0.37
     Wul
    -0.37
     dispuesto
    -0.37
    POSITIVE LOGITS
     Amish
    0.93
     Mennon
    0.85
     EconPapers
    0.56
    Lancaster
    0.56
     pinulongan
    0.56
     buggy
    0.55
    IntoConstraints
    0.52
     Brethren
    0.51
     Lancaster
    0.50
     pacif
    0.50
    Activations Density 0.086%

    No Known Activations