© 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. 24-GEMMASCOPE-RES-16K
    11. 5478
    Prev
    Next
    INDEX
    Explanations

    references to emotional or psychological distress

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

    Follows "removed", "an", or "(" tokens

    np_acts-logits-general · gemini-2.0-flash

    removed his, an upper, activity during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.62
     beginnetje
    -0.56
    WriteTagHelper
    -0.51
     myſelf
    -0.48
    parsedMessage
    -0.48
     Rtl
    -0.47
    saraba
    -0.46
    ‍♂️
    -0.46
    valentino
    -0.46
    ContentValues
    -0.46
    POSITIVE LOGITS
     secundario
    0.43
     للاسماء
    0.40
     rodillas
    0.40
     habido
    0.40
     cementerio
    0.38
     secundaria
    0.38
     hidráulica
    0.37
     producciones
    0.35
     profundidad
    0.35
     asociados
    0.35
    Activations Density 0.045%

    No Known Activations