© 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. 21-GEMMASCOPE-RES-16K
    11. 12787
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names related to specific people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.57
     Elbe
    -0.52
    WIS
    -0.51
     bụ
    -0.51
    }")]
    -0.50
     Osama
    -0.50
    thail
    -0.49
    Skocz
    -0.49
    )$}
    -0.49
     Mombasa
    -0.49
    POSITIVE LOGITS
     Armenian
    1.06
     Armenia
    0.98
     armen
    0.95
     Yerevan
    0.90
    Armen
    0.88
     Armenians
    0.86
    Armenia
    0.86
    armen
    0.84
     Armen
    0.83
    erevan
    0.72
    Activations Density 0.059%

    No Known Activations