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. 20-GEMMASCOPE-RES-16K
    6. 6505
    Prev
    Next
    INDEX
    Explanations

    contextual phrases related to business operations and trading strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     تانيه
    -0.94
     houſe
    -0.94
     ſmall
    -0.88
     المعيارى
    -0.82
     greateſt
    -0.79
     Cæsar
    -0.78
     reaſon
    -0.78
     pleaſure
    -0.77
     ſtate
    -0.76
     Houſe
    -0.74
    POSITIVE LOGITS
     những
    0.66
    )$/,
    0.52
     các
    0.44
     sehe
    0.43
    )}</
    0.43
     một
    0.41
    Petite
    0.41
     compter
    0.41
    вік
    0.40
    vertido
    0.40
    Activations Density 0.008%

    No Known Activations