© 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. 10805
    Prev
    Next
    INDEX
    Explanations

    names of government positions and officials

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

    ministers or ministries

    np_acts-logits-general · gemini-2.0-flash

    Minister

    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
     препратки
    -0.49
    migrationBuilder
    -0.48
    TagMode
    -0.41
    脚注の使い方
    -0.40
    ThroughAttribute
    -0.39
     armas
    -0.37
    oredCriteria
    -0.37
     Autónoma
    -0.36
    OGND
    -0.35
    IGENCE
    -0.35
    POSITIVE LOGITS
     Minister
    1.85
     minister
    1.82
    Minister
    1.73
     ministers
    1.60
    minister
    1.57
     Ministers
    1.55
     ministerial
    1.42
     ministry
    1.41
     ministre
    1.36
     Ministry
    1.34
    Activations Density 0.310%

    No Known Activations