© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14428
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "see" and its variations, indicating visual perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "see"

    np_acts-logits-general · gemini-2.0-flash

    forms of the word see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    athus
    -0.47
     McCormack
    -0.41
     Gru
    -0.41
     frango
    -0.39
     husband
    -0.39
    onUpdate
    -0.38
     dolci
    -0.38
     suom
    -0.37
    ghum
    -0.37
    私の
    -0.37
    POSITIVE LOGITS
    see
    1.12
    Seen
    1.06
     see
    1.06
    See
    1.02
    seen
    0.99
     See
    0.98
     SEE
    0.96
    Saw
    0.94
     sees
    0.94
    saw
    0.92
    Activations Density 0.152%

    No Known Activations