© 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. 9535
    Prev
    Next
    INDEX
    Explanations

    time-related references, particularly concerning durations such as days, months, and years

    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
    enumii
    -0.72
     Theſe
    -0.71
    providedIn
    -0.70
     cherchés
    -0.64
     Majefty
    -0.63
     Ordovician
    -0.63
    });
    
    
    -0.60
    <>());
    -0.59
     Eſ
    -0.58
     henvisninger
    -0.58
    POSITIVE LOGITS
    preventDefault
    0.62
     abbond
    0.59
     straight
    0.56
    以上
    0.54
     apiece
    0.52
    BaseAdapter
    0.51
    quarters
    0.51
     inteiro
    0.51
    солю
    0.49
    Kaynakça
    0.48
    Activations Density 0.174%

    No Known Activations