© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 205
    Prev
    Next
    INDEX
    Explanations

    details related to various types of medical treatments and their effectiveness

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

    Mathematical or biological variables/symbols

    np_acts-logits-general · gemini-2.0-flash

    medical and biological contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of medical terms or conditions, particularly when separated by commas or conjunctions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.77
    ValueStyle
    -0.63
    Lähteet
    -0.56
    AddHtmlAttribute
    -0.55
    writeField
    -0.55
    Cyfarwyddwr
    -0.54
    ientôt
    -0.53
    MarshalTo
    -0.51
    __':
    -0.49
     AssemblyTitle
    -0.49
    POSITIVE LOGITS
     defStyle
    0.35
     ✭✭
    0.32
    donna
    0.31
     typelib
    0.30
    TargetException
    0.30
     ViewHolder
    0.30
    inigung
    0.29
    belea
    0.29
    disposing
    0.29
    unnitel
    0.28
    Activations Density 0.709%

    No Known Activations