© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11054
    Prev
    Next
    INDEX
    Explanations

    references to "fine" as a descriptor or quality related to materials or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.61
     purpoſe
    -0.59
    webElement
    -0.57
     Verſ
    -0.54
    WriteBarrier
    -0.53
     houſe
    -0.53
     Monfieur
    -0.52
    featureID
    -0.51
     indígen
    -0.51
     erſt
    -0.50
    POSITIVE LOGITS
     Fine
    0.74
    Fine
    0.71
     fine
    0.69
    fine
    0.64
     PM
    0.60
     FINE
    0.58
    PM
    0.56
     fund
    0.51
     fond
    0.47
     pm
    0.47
    Activations Density 0.277%

    No Known Activations