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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2032
    Prev
    Next
    INDEX
    Explanations

    "we" and its variations, indicating a focus on the subject's actions or observations in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.05
     Theſe
    -0.92
    ^(@)
    -0.89
     Jefus
    -0.88
    MessageOf
    -0.83
    RTEE
    -0.78
    posedge
    -0.78
    extAlignment
    -0.78
    openConnection
    -0.77
    NUMX
    -0.76
    POSITIVE LOGITS
     also
    0.60
     note
    0.57
     staden
    0.52
     then
    0.51
    midler
    0.48
     escaleras
    0.47
     try
    0.47
    try
    0.47
     specifically
    0.47
    Note
    0.47
    Activations Density 0.564%

    No Known Activations