© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3654
    Prev
    Next
    INDEX
    Explanations

    references to local governance and community institutions in Kerala

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.70
     Harts
    -0.57
    ReusableCell
    -0.54
     Tennessee
    -0.53
     Voigt
    -0.53
     Lodi
    -0.49
     Waikato
    -0.48
     noires
    -0.48
     Atlanta
    -0.48
    wickshire
    -0.48
    POSITIVE LOGITS
     Kerala
    0.93
     Kochi
    0.86
    Kerala
    0.83
     Malabar
    0.77
     Cochin
    0.74
     Malayalam
    0.72
     Thr
    0.70
     kerala
    0.69
     OFDb
    0.62
    +#+#
    0.62
    Activations Density 0.097%

    No Known Activations