© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 485
    Prev
    Next
    INDEX
    Explanations

    the term "Finally" or its variations, indicating a concluding statement

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

    the word "Finally" and its surrounding punctuation or context within the text

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

    finally,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Anſ
    -0.93
     Efq
    -0.91
     myſelf
    -0.89
     purpoſe
    -0.86
     itſelf
    -0.86
    ſelf
    -0.85
     leſs
    -0.83
     uſe
    -0.82
    neſs
    -0.81
     Majefty
    -0.80
    POSITIVE LOGITS
     Lastly
    1.12
    Lastly
    1.12
     Finally
    0.98
    Finally
    0.94
     finally
    0.92
     lastly
    0.91
     but
    0.91
    finally
    0.87
     bref
    0.78
     FINALLY
    0.74
    Activations Density 0.032%

    No Known Activations