Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7797
    Prev
    Next
    INDEX
    Explanations

    terminology related to statistical modeling and approximation methods

    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
    tagHelperRunner
    -0.59
    mar
    -0.37
    Enllaces
    -0.36
    ried
    -0.35
    ziplin
    -0.34
    &&&
    -0.34
    colate
    -0.33
     Immig
    -0.33
     مها
    -0.33
    jsonwebtoken
    -0.32
    POSITIVE LOGITS
    principalTable
    0.54
    PostInfinity
    0.52
     accuracy
    0.52
    模型
    0.48
    互联网档案馆
    0.48
    InputTagHelper
    0.48
     predicting
    0.47
     prediction
    0.46
    Tikang
    0.46
     améli
    0.45
    Activations Density 1.751%

    No Known Activations