© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1774
    Prev
    Next
    INDEX
    Explanations

    activities related to outdoor sports and recreation

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

    Hobbies and recreational activities

    np_acts-logits-general · gemini-2.0-flash

    sport and hobby activities

    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
    )))));
    -0.52
     ویکی‌پدی
    -0.44
    zungs
    -0.43
    bootstrapcdn
    -0.41
    ))));
    -0.39
     accused
    -0.38
    })));
    -0.38
    asteroide
    -0.37
    )));
    -0.37
     despe
    -0.37
    POSITIVE LOGITS
     amateurs
    0.65
     hobby
    0.61
     hobbies
    0.57
    hobby
    0.53
     recreational
    0.51
     esporte
    0.51
     weekends
    0.50
     Hobbies
    0.50
     amateur
    0.49
     enthusiasts
    0.48
    Activations Density 0.127%

    No Known Activations