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. 6671
    Prev
    Next
    INDEX
    Explanations

    terms and roles related to academic disciplines and scholarly research institutions

    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
     COMMERCIAL
    -0.40
     REQUIREMENTS
    -0.40
     empresarial
    -0.39
     functionality
    -0.39
     requirements
    -0.39
    новништво
    -0.37
     COMERC
    -0.37
     improvements
    -0.36
     Improvements
    -0.36
     Functionality
    -0.36
    POSITIVE LOGITS
     scholars
    0.61
     JSTOR
    0.55
    onAttach
    0.54
     scholar
    0.53
     scholarly
    0.52
    ']>
    0.52
     analyzing
    0.51
    分析
    0.51
     EconPapers
    0.51
     Professor
    0.50
    Activations Density 0.410%

    No Known Activations