© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 6412
    Prev
    Next
    INDEX
    Explanations

    specific adjectives and descriptive phrases that enhance and personalize narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.80
    RegressionTest
    -0.68
    SharedDtor
    -0.65
    expandindo
    -0.63
     propOrder
    -0.62
    featureID
    -0.61
     ویکی‌پدی
    -0.60
    .*")]
    -0.58
    XmlAccessorType
    -0.57
    OGND
    -0.57
    POSITIVE LOGITS
     truly
    0.54
     refreshing
    0.48
     wahr
    0.46
     must
    0.46
     wahren
    0.44
     true
    0.42
     veritable
    0.42
     breath
    0.42
     rare
    0.42
     uniquely
    0.41
    Activations Density 0.316%

    No Known Activations