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. 3020
    Prev
    Next
    INDEX
    Explanations

    references to books and articles

    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
     Shakspeare
    -0.58
    KommentareTeilen
    -0.54
    layui
    -0.51
     tweeting
    -0.49
     ويكيميديا
    -0.48
     MyBatis
    -0.48
    stateProvider
    -0.47
     alér
    -0.47
    rendering
    -0.46
     Shaksp
    -0.46
    POSITIVE LOGITS
     contain
    1.11
     contains
    1.05
     describe
    0.94
    contains
    0.91
     discusses
    0.90
     describes
    0.89
    contain
    0.88
     addresses
    0.88
     discuss
    0.88
     Contain
    0.85
    Activations Density 0.530%

    No Known Activations