Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8526
    Prev
    Next
    INDEX
    Explanations

    structured data or tabular formats often associated with databases or programming

    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
     Dickinson
    -0.87
     Chamb
    -0.79
     Chambers
    -0.78
     CHAM
    -0.78
    itz
    -0.76
     Spencer
    -0.74
     Chak
    -0.70
     chambers
    -0.70
    CHAM
    -0.70
     TZ
    -0.69
    POSITIVE LOGITS
     Poplar
    0.71
     Wiley
    0.70
     Monaghan
    0.70
     Ascot
    0.69
     Biggs
    0.68
     banana
    0.67
     Higgins
    0.67
     bananas
    0.67
     Fabio
    0.67
     Lili
    0.64
    Activations Density 1.373%

    No Known Activations