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. 14643
    Prev
    Next
    INDEX
    Explanations

    phrases expressing excessiveness or abundance

    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
     blij
    -0.34
    MessageTagHelper
    -0.34
     graphically
    -0.33
    毫不
    -0.33
     uitz
    -0.32
     miglia
    -0.32
    毫无
    -0.31
     exceptionally
    -0.31
     espero
    -0.30
     handsomely
    -0.30
    POSITIVE LOGITS
     Too
    0.88
     too
    0.82
     TOO
    0.81
    too
    0.75
    Too
    0.75
    UnusedPrivate
    0.72
    太多
    0.72
    太多的
    0.71
     demasiado
    0.68
     terlalu
    0.68
    Activations Density 0.370%

    No Known Activations