© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16138
    Prev
    Next
    INDEX
    Explanations

    references to the pronouns "you" and "I" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     tarko
    -0.38
     voici
    -0.36
     is
    -0.29
     médié
    -0.29
     tampoco
    -0.28
     will
    -0.27
     spørs
    -0.27
     énergé
    -0.27
     bonté
    -0.27
     myös
    -0.26
    POSITIVE LOGITS
     Administrativna
    0.99
    ьаж
    0.94
    aarrggbb
    0.93
     autorytatywna
    0.90
    <pad>
    0.90
    <unused43>
    0.90
    <unused8>
    0.90
    [@BOS@]
    0.90
    <unused74>
    0.90
    <unused3>
    0.90
    Activations Density 0.164%

    No Known Activations