© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8433
    Prev
    Next
    INDEX
    Explanations

    phrases that express questioning or evaluating actions and outcomes

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

    elaboration or continuation

    np_acts-logits-general · gemini-2.0-flash

    also discussion or expert testimony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.97
     itſelf
    -0.96
     дописавши
    -0.93
     myſelf
    -0.90
     فريبيس
    -0.89
     themſelves
    -0.88
    Datuak
    -0.87
    ſelves
    -0.85
    ſelf
    -0.85
     faſt
    -0.83
    POSITIVE LOGITS
     also
    0.72
     Also
    0.57
     mention
    0.55
     include
    0.54
    ALSO
    0.54
     particularly
    0.53
    also
    0.52
     επίσης
    0.52
    Also
    0.51
     notably
    0.51
    Activations Density 0.736%

    No Known Activations