© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    relationships and correlations between different concepts or variables

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

    "[Something] between [something]" broadly construed

    np_acts-logits-general · gemini-2.0-flash

    connection between

    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
    ViewImports
    -0.46
     Савезне
    -0.37
    ronpa
    -0.32
    reportWebVitals
    -0.31
    quias
    -0.31
     SwitchCompat
    -0.30
    slidesToShow
    -0.29
    WireFormatLite
    -0.29
     OnEnable
    -0.29
    </table>
    -0.28
    POSITIVE LOGITS
     between
    2.78
    between
    2.28
     между
    2.16
    Between
    2.16
     Between
    2.16
     zwischen
    2.13
     tussen
    2.00
     mellan
    1.98
     між
    1.90
     pomiędzy
    1.88
    Activations Density 0.904%

    No Known Activations