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. 5-GEMMASCOPE-RES-16K
    6. 1591
    Prev
    Next
    INDEX
    Explanations

    terminology related to acceleration and catalysis in chemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoid
    -0.59
     thống
    -0.55
     else
    -0.51
    ]_
    -0.49
     Havel
    -0.49
     Schmitz
    -0.48
    Nep
    -0.48
     Vorg
    -0.47
     disposable
    -0.47
     River
    -0.46
    POSITIVE LOGITS
     acceleration
    1.97
     accelerate
    1.83
    acceler
    1.80
     accelerates
    1.78
     Acceleration
    1.77
     accelerated
    1.76
     accelerating
    1.72
     acceler
    1.68
    Acceler
    1.67
     Acceler
    1.63
    Activations Density 0.192%

    No Known Activations