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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114919
    Prev
    Next
    INDEX
    Explanations

    the word "both"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chère
    -0.28
     autre
    -0.27
     enx
    -0.24
     etc
    -0.23
    二
    -0.23
     after
    -0.23
     másik
    -0.23
    I
    -0.23
     altro
    -0.23
    ฯ
    -0.23
    POSITIVE LOGITS
    Personendaten
    1.06
     autorytatywna
    0.90
     myſelf
    0.84
    [@BOS@]
    0.84
    <unused41>
    0.84
    <unused28>
    0.84
    <unused43>
    0.84
    <unused74>
    0.84
     nahilalakip
    0.84
    <unused3>
    0.83
    Activations Density 0.039%

    No Known Activations