© 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. 28-GEMMASCOPE-RES-16K
    11. 8030
    Prev
    Next
    INDEX
    Explanations

    statements about beliefs and straightforward assertions regarding various topics

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

    Follows first-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    company names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confé
    -0.41
     tío
    -0.36
     templado
    -0.34
     tirantes
    -0.34
     conferencias
    -0.31
    érieur
    -0.30
     capteur
    -0.30
     pró
    -0.30
     crucero
    -0.30
     mengangg
    -0.29
    POSITIVE LOGITS
    참고
    0.70
    цездатний
    0.69
     EconPapers
    0.61
    脚注の使い方
    0.60
     himo
    0.59
     transfieras
    0.59
     AssemblyProduct
    0.58
    MigrationBuilder
    0.58
    +:+
    0.57
     disambiguazione
    0.57
    Activations Density 2.094%

    No Known Activations