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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12308
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and experimental methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⎩
    -0.47
    前后
    -0.39
     both
    -0.39
     off
    -0.39
     to
    -0.38
    kreuz
    -0.37
     Ro
    -0.37
     Bar
    -0.36
     cotta
    -0.36
     दोनों
    -0.35
    POSITIVE LOGITS
     للاسماء
    1.00
     Monfieur
    0.93
     Efq
    0.91
     purpoſe
    0.89
     للمعارف
    0.87
     fevere
    0.86
     ſte
    0.86
     AttributeSet
    0.86
     fubject
    0.85
     AssemblyTitle
    0.85
    Activations Density 1.028%

    No Known Activations