© 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. 22-GEMMASCOPE-RES-16K
    11. 8296
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to clinical studies and drug treatments, particularly involving the drug efalizumab

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

    Followed by language codes ("al", "iz")

    np_acts-logits-general · gemini-2.0-flash

    efalizumab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AND
    -1.25
    And
    -1.25
     And
    -1.24
    ＆
    -1.02
    and
    -0.98
    アンド
    -0.97
    和
    -0.95
     \&
    -0.94
     &
    -0.93
    \&
    -0.92
    POSITIVE LOGITS
    PreferredItem
    0.71
    دانشنامهٔ
    0.67
    Aiheesta
    0.57
    Portail
    0.56
    Kaynakça
    0.56
    !*\
    0.53
    /**
    0.52
    ensement
    0.52
    Lähteet
    0.51
    setCellValue
    0.51
    Activations Density 1.473%

    No Known Activations