© 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. 23-GEMMASCOPE-RES-16K
    11. 6168
    Prev
    Next
    INDEX
    Explanations

    references to financial support and grants from government agencies or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bulgarian
    -0.65
     Somali
    -0.64
     Ghanaians
    -0.63
     Salisbury
    -0.63
     Ugandan
    -0.63
     Volga
    -0.62
     GenerationType
    -0.62
     Afghans
    -0.62
     Sochi
    -0.61
    ParallelGroup
    -0.61
    POSITIVE LOGITS
     Taiwan
    1.22
    Taiwan
    1.10
     Taipei
    1.06
     Taiwanese
    0.99
     Formosa
    0.91
     taiwan
    0.89
     Tsai
    0.83
     ROC
    0.71
     Kuo
    0.71
    Tai
    0.70
    Activations Density 0.086%

    No Known Activations