© 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. 14074
    Prev
    Next
    INDEX
    Explanations

    elements that contribute to the humor and absurdity in the narrative

    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
    非常的
    -1.12
     Whilst
    -1.08
    Whilst
    -1.05
     diatas
    -1.04
     coté
    -1.02
     dimana
    -1.01
     didalam
    -1.00
     poichè
    -0.98
     whilst
    -0.96
     pò
    -0.94
    POSITIVE LOGITS
     freilich
    1.21
    twimg
    0.96
     NDEBUG
    0.94
     ostensibly
    0.91
     gleaming
    0.89
     persino
    0.87
     voilà
    0.87
     CHECKBOX
    0.86
    MigrationBuilder
    0.86
     résumé
    0.85
    Activations Density 1.159%

    No Known Activations