© 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. 4775
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fiction" and related terms

    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
     betweenstory
    -0.45
     Sonnen
    -0.39
     raza
    -0.35
     colombiano
    -0.35
     Drei
    -0.33
    WaitGroup
    -0.33
     Steuerung
    -0.33
     начин
    -0.33
     puffy
    -0.33
     médicas
    -0.33
    POSITIVE LOGITS
    MessageTagHelper
    0.73
    URLException
    0.70
     tick
    0.69
     Tick
    0.68
     ſta
    0.68
     ſind
    0.67
     ſtand
    0.67
    tick
    0.66
    Tick
    0.65
     poffe
    0.65
    Activations Density 0.319%

    No Known Activations