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. 21-GEMMASCOPE-RES-16K
    6. 669
    Prev
    Next
    INDEX
    Explanations

    components related to research methods and legal principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.94
     дописавши
    -0.89
     consultato
    -0.86
     Monfieur
    -0.83
     myſelf
    -0.81
     houſe
    -0.81
     елның
    -0.80
     ſen
    -0.80
     ſch
    -0.77
     ſtate
    -0.77
    POSITIVE LOGITS
     put
    0.61
     being
    0.57
     that
    0.54
     actually
    0.49
     which
    0.48
     while
    0.47
     yang
    0.45
     set
    0.44
    뀌
    0.44
     advanced
    0.43
    Activations Density 0.707%

    No Known Activations