© 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. 24-GEMMASCOPE-RES-16K
    11. 4634
    Prev
    Next
    INDEX
    Explanations

    references to locations and geographic names in a context discussing animals or shelters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    US states and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    US states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '{@
    -0.69
     Juz
    -0.57
     /\.(
    -0.57
    ########.
    -0.56
     gerekiyor
    -0.52
    podar
    -0.51
    ++)
    -0.51
     uș
    -0.50
     esboço
    -0.50
     picioare
    -0.50
    POSITIVE LOGITS
     PA
    1.35
     TX
    1.29
     NC
    1.28
     GA
    1.23
     MN
    1.23
     AZ
    1.22
     TN
    1.21
     NJ
    1.21
     CA
    1.20
     FL
    1.18
    Activations Density 0.618%

    No Known Activations