© 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. 18-GEMMASCOPE-RES-16K
    11. 467
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quality or condition, particularly relating to health and well-being

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

    "well" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    well followed by hyphen or known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     religieuses
    -0.64
     industriel
    -0.53
    сылкі
    -0.52
    intercept
    -0.52
     مصرى
    -0.51
    venirs
    -0.51
    atalos
    -0.51
    Draft
    -0.51
     تعدى
    -0.50
     Anschluss
    -0.50
    POSITIVE LOGITS
     Well
    0.86
     WELL
    0.85
     wells
    0.83
     Welles
    0.81
    Well
    0.79
    Wells
    0.76
     Wells
    0.74
     well
    0.73
     Bem
    0.72
     CURIAM
    0.72
    Activations Density 0.124%

    No Known Activations