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. 7742
    Prev
    Next
    INDEX
    Explanations

    proper protocols and methods related to waste management and healthcare

    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
     utafitiHapana
    -0.70
    $_['
    -0.48
     denk
    -0.47
    ValueStyle
    -0.47
    Zunanje
    -0.46
    AnchorTagHelper
    -0.46
    AntiForgeryToken
    -0.46
    Билгалдахарш
    -0.45
     busiest
    -0.45
     հղումներ
    -0.45
    POSITIVE LOGITS
     properly
    0.60
     Thorough
    0.59
     Properly
    0.58
     adequately
    0.57
    もしっかり
    0.56
    Sufficient
    0.56
     Adequate
    0.56
    きちんと
    0.55
    Proper
    0.54
     Sufficient
    0.54
    Activations Density 0.456%

    No Known Activations