© 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. 10-GEMMASCOPE-RES-16K
    11. 15852
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or reference specific content, criteria, or relationships in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvoit
    -0.66
     enfans
    -0.66
     feroit
    -0.61
     Infór
    -0.59
     démocr
    -0.58
     BrowserModule
    -0.57
    majánló
    -0.56
    iſen
    -0.54
     larmes
    -0.53
     âmes
    -0.53
    POSITIVE LOGITS
     following
    1.59
    following
    1.27
     Following
    1.18
     FOLLOWING
    1.16
    Following
    1.13
     seguinte
    1.00
     følgende
    0.98
     suivantes
    0.96
     suivants
    0.95
     suivante
    0.94
    Activations Density 0.225%

    No Known Activations