© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2218
    Prev
    Next
    INDEX
    Explanations

    references to soccer actions and plays

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

    Follows "off" or "<start_of_turn>"

    np_acts-logits-general · gemini-2.0-flash

    possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.51
     transfieras
    -0.43
    queryInterface
    -0.41
     zdecydow
    -0.38
    outWeight
    -0.38
     jakim
    -0.35
    BeforeAll
    -0.35
    interopRequire
    -0.35
     orejas
    -0.34
    destroyAll
    -0.33
    POSITIVE LOGITS
     Possession
    0.60
     possessions
    0.58
     '\\;'
    0.57
    Poss
    0.57
    possession
    0.56
     possession
    0.55
     Poss
    0.52
    XmlAccessType
    0.49
     StringTokenizer
    0.49
     poffe
    0.49
    Activations Density 0.065%

    No Known Activations