© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15346
    Prev
    Next
    INDEX
    Explanations

    expressions of relief and positivity in various contexts

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

    expressions indicating a long-awaited or overdue resolution/culmination—marking that something finally happens or reaches a proper state.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    expressions of relief or satisfaction after a long wait or struggle has ended.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Lower
    -0.37
     verder
    -0.34
    StoreMessageInfo
    -0.33
    ówek
    -0.33
    ster
    -0.33
     lẻ
    -0.33
     obrazov
    -0.33
     <>",
    -0.32
     boule
    -0.32
    ніципалі
    -0.32
    POSITIVE LOGITS
     finally
    0.91
    finally
    0.89
     enfin
    0.84
     endlich
    0.81
     FINALLY
    0.80
     наконец
    0.78
    Finally
    0.76
     Endlich
    0.75
     Finally
    0.73
     finalmente
    0.70
    Activations Density 0.224%

    No Known Activations