Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 61623
    Prev
    Next
    INDEX
    Explanations

    references to tournaments and competitions in sports

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

    sports tournaments and competitions

    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
    脚注の使い方
    -0.61
    OrEqualTo
    -0.48
    ChromeDriver
    -0.47
     Comprometido
    -0.45
     Италијани
    -0.44
    OCCURRED
    -0.43
    Enlaces
    -0.42
    Personendaten
    -0.42
    новништво
    -0.41
     nakalista
    -0.40
    POSITIVE LOGITS
    msgTypes
    0.46
     TDA
    0.44
     tournament
    0.42
    }$​
    0.41
     Turnier
    0.41
     tourney
    0.40
     Tournament
    0.40
     abroad
    0.40
     spilt
    0.39
    estero
    0.38
    Activations Density 0.008%

    No Known Activations