© 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. 852
    Prev
    Next
    INDEX
    Explanations

    references to locations and specific entities involved in historical contexts

    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
     Parisian
    -1.13
     CANADIAN
    -1.11
    Ukrainian
    -1.10
    Brazilian
    -1.10
    Norwegian
    -1.10
    Mexican
    -1.09
    Canadian
    -1.09
    Scottish
    -1.09
    Welsh
    -1.06
     Berliner
    -1.05
    POSITIVE LOGITS
     India
    1.08
     Italy
    1.06
     Germany
    0.99
     France
    0.97
     Spain
    0.95
     Ireland
    0.95
     Japan
    0.94
     Nigeria
    0.93
     Australia
    0.93
     Canada
    0.92
    Activations Density 0.755%

    No Known Activations