© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 890
    Prev
    Next
    INDEX
    Explanations

    key entities associated with locations and their characteristics

    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
     werking
    -0.58
     PFC
    -0.57
     propOrder
    -0.54
     württemberg
    -0.54
     Vallejo
    -0.53
    bronn
    -0.52
     Maine
    -0.50
     heuer
    -0.50
    CppMethod
    -0.49
     wikipagina
    -0.49
    POSITIVE LOGITS
     Dutch
    1.84
     Holland
    1.65
     Netherlands
    1.64
    Dutch
    1.58
     Amsterdam
    1.51
    Holland
    1.45
     Dutchman
    1.45
     dutch
    1.45
    Netherlands
    1.44
     Van
    1.42
    Activations Density 0.192%

    No Known Activations