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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6622
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to forms and user input interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    RegistryLite
    -0.81
    tagHelperRunner
    -0.79
    TypedDataSet
    -0.77
    setVerticalGroup
    -0.73
    hyrchwyd
    -0.72
    awtextra
    -0.71
     queſta
    -0.67
    IVEREF
    -0.66
    expandindo
    -0.65
     שוליים
    -0.65
    POSITIVE LOGITS
    Sha
    0.27
     sha
    0.27
     writer
    0.26
     kapa
    0.26
     rato
    0.26
    先是
    0.26
    >')
    0.25
    头
    0.25
    "");
    0.25
    ẫy
    0.25
    Activations Density 0.179%

    No Known Activations