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. 2126
    Prev
    Next
    INDEX
    Explanations

    punctuations and their context in sentences

    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
     <<<<<<<<<<<<<<
    -0.47
    writeFieldEnd
    -0.42
     inférieur
    -0.34
     inférieure
    -0.33
    invokeLater
    -0.33
    +#+#
    -0.32
    <0xE2>
    -0.32
    UseVisualStyle
    -0.31
     and
    -0.31
    WithMany
    -0.30
    POSITIVE LOGITS
     dieſem
    0.68
    <unused52>
    0.66
    <unused74>
    0.66
    <unused8>
    0.66
     dieſen
    0.66
    [@BOS@]
    0.66
    <unused23>
    0.66
    <unused51>
    0.66
    <unused28>
    0.66
    <unused14>
    0.65
    Activations Density 0.341%

    No Known Activations