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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84345
    Prev
    Next
    INDEX
    Explanations

    references to various "leagues"

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

    sports leagues, cups, and contests

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     "
    -0.48
     '
    -0.46
    Autowired
    -0.43
     is
    -0.42
     Has
    -0.42
    ")"
    -0.40
     ”
    -0.40
     ''
    -0.39
     Pfer
    -0.39
    thenReturn
    -0.39
    POSITIVE LOGITS
     League
    1.31
     LEAGUE
    1.29
     league
    1.23
    League
    1.23
    league
    1.14
     Leagues
    1.05
     leagues
    0.98
     ſtate
    0.88
     ſche
    0.88
     ligue
    0.85
    Activations Density 0.008%

    No Known Activations