© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 8025
    Prev
    Next
    INDEX
    Explanations

    references to cultural heritage and crises impacting communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulumi
    -0.42
     unknownFields
    -0.41
    PyExc
    -0.37
     pouvoit
    -0.36
    omiast
    -0.36
     lenker
    -0.35
     disponibilità
    -0.35
    Wanted
    -0.34
    osz
    -0.34
     feroit
    -0.34
    POSITIVE LOGITS
     affected
    2.17
     impacted
    1.72
    affected
    1.66
     Affected
    1.66
    Affected
    1.51
     afflicted
    1.43
     hit
    1.40
     afectados
    1.40
     effected
    1.38
     afectado
    1.35
    Activations Density 0.738%

    No Known Activations