© 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. 12362
    Prev
    Next
    INDEX
    Explanations

    words related to case reports and clinical observations

    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
     itſelf
    -0.82
     snippetHide
    -0.80
    réhen
    -0.79
     poffible
    -0.78
     himſelf
    -0.76
     myſelf
    -0.75
     ſch
    -0.74
     niedersachsen
    -0.71
     eſt
    -0.71
     auffi
    -0.71
    POSITIVE LOGITS
     fucking
    0.86
    fucking
    0.73
    ಠ
    0.73
     mierda
    0.72
     FUCKING
    0.72
     goddamn
    0.70
     piss
    0.66
    でございます
    0.65
     hereby
    0.65
    fuck
    0.65
    Activations Density 1.492%

    No Known Activations