© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 6890
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to demographics and clinical variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ham
    -1.05
     Ham
    -0.98
     HAM
    -0.97
     Hammers
    -0.96
     Hammond
    -0.92
     Hampshire
    -0.84
     ham
    -0.83
     Hamza
    -0.79
     Hamma
    -0.72
     Hamster
    -0.71
    POSITIVE LOGITS
     Erik
    0.75
     Gog
    0.75
     Garcia
    0.74
     Crawford
    0.73
     Fang
    0.70
     Garland
    0.68
    Erik
    0.67
     LRT
    0.65
     PTC
    0.64
    Crawford
    0.63
    Activations Density 1.637%

    No Known Activations