© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14582
    Prev
    Next
    INDEX
    Explanations

    references to playoff qualifications and standings in sports contexts

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

    Teams or players making playoffs/postseason

    np_acts-logits-general · gemini-2.0-flash

    qualifying for playoffs

    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
    
    -0.65
    interopRequire
    -0.40
     EconPapers
    -0.39
     nakalista
    -0.37
    Források
    -0.37
     synthetic
    -0.37
     ask
    -0.36
     fair
    -0.36
    TypedDataSet
    -0.35
     String
    -0.35
    POSITIVE LOGITS
    komna
    0.53
    berdayakan
    0.53
    AnimationsModule
    0.51
     springfox
    0.50
     Qualifying
    0.49
    othelioma
    0.49
    accéder
    0.47
    admission
    0.46
    ToBounds
    0.46
     qualifying
    0.45
    Activations Density 0.138%

    No Known Activations