© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1370
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to player performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Fantasy" followed by golf or sports

    np_acts-logits-general · gemini-2.0-flash

    fantasy golf drafts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commerciaux
    -0.54
    CJK
    -0.53
     spirituale
    -0.50
    Nomenclature
    -0.49
     gangen
    -0.46
    مراجع
    -0.46
    Cameras
    -0.46
     poveznice
    -0.46
     commerciales
    -0.45
    imread
    -0.45
    POSITIVE LOGITS
     fantasy
    1.27
     Fantasy
    1.07
    Fantasy
    1.01
    fantasy
    0.97
    antasy
    0.83
     FANT
    0.80
     Draft
    0.80
    TagHelper
    0.79
    Draft
    0.75
     dynasty
    0.73
    Activations Density 0.089%

    No Known Activations