© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4396
    Prev
    Next
    INDEX
    Explanations

    phrases related to exiting or being outside

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

    The token "out" starts a phrase

    np_acts-logits-general · gemini-2.0-flash

    out of, out on, out in

    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
     ainfi
    -0.92
     vectorielle
    -0.70
     fédé
    -0.68
     zoude
    -0.66
    retudo
    -0.66
     quelcon
    -0.66
     feroit
    -0.64
     plufieurs
    -0.64
     vœ
    -0.63
     dezelve
    -0.63
    POSITIVE LOGITS
     Out
    1.23
     OUT
    1.22
     out
    1.22
    Out
    1.20
    out
    1.13
    OUT
    0.98
    EOUT
    0.97
     outs
    0.87
    outs
    0.85
     Hout
    0.83
    Activations Density 0.127%

    No Known Activations