© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4294
    Prev
    Next
    INDEX
    Explanations

    the word "out" in various contexts and its associations with concepts of directionality or escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TCR
    -0.99
    etheless
    -0.94
    theless
    -0.94
    locene
    -0.85
    quelize
    -0.84
    kaper
    -0.83
    MemoryWarning
    -0.83
     AssemblyProduct
    -0.81
    polation
    -0.81
    cosity
    -0.81
    POSITIVE LOGITS
     OUT
    1.63
     Out
    1.53
     out
    1.52
    Out
    1.48
    out
    1.47
    OUT
    1.24
     outs
    1.18
    getOut
    1.08
     Outs
    0.99
    アウト
    0.96
    Activations Density 0.117%

    No Known Activations