© 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. 17-GEMMASCOPE-RES-16K
    6. 1956
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or negation regarding consensus and effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scénario
    -0.61
     فريبيس
    -0.52
    !!!!!!!
    -0.49
    !!!!!!
    -0.49
     """
    
    -0.48
    !!!!!!!!!!
    -0.48
     jaunes
    -0.48
    !!!!!
    -0.47
    quedas
    -0.47
    !!!!!!!!
    -0.46
    POSITIVE LOGITS
     directly
    0.98
     fully
    0.95
     outright
    0.93
     exact
    0.89
     overtly
    0.88
    directly
    0.87
     Directly
    0.86
     formally
    0.85
     definitive
    0.83
     definitively
    0.82
    Activations Density 0.843%

    No Known Activations