© 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. 33-GEMMASCOPE-RES-16K
    11. 9895
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to fly fishing and the associated equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.58
     JpaRepository
    -0.58
     autorytatywna
    -0.53
    ChildScrollView
    -0.53
     defaultstate
    -0.50
    +#+
    -0.49
     Autorizaciones
    -0.49
     Maze
    -0.49
    indd
    -0.49
    __*/
    -0.48
    POSITIVE LOGITS
     fly
    1.09
     flies
    0.89
    Fly
    0.89
    fly
    0.86
     Fly
    0.85
    flies
    0.73
     FLY
    0.69
     Flies
    0.69
     casting
    0.66
    FLY
    0.66
    Activations Density 0.075%

    No Known Activations