© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 564
    Prev
    Next
    INDEX
    Explanations

    phrases related to expert advice and patient care communication

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

    professional, instructional, or educational terminology and references, especially those related to teaching, expertise, healthcare, and guidance.

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @ywhp2c8tjm

    preceding suggestions or instructions

    np_acts-logits-general · gemini-2.0-flash

    giving advice and information

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    AnchorStyles
    -0.40
     AssemblyCulture
    -0.35
     Island
    -0.35
     horloge
    -0.31
     gebe
    -0.31
     malat
    -0.31
     Islands
    -0.31
     Nort
    -0.30
     kwar
    -0.30
    impro
    -0.29
    POSITIVE LOGITS
    SourceChecksum
    0.60
    complexContent
    0.52
    Chham
    0.52
    inemann
    0.50
    ttemberg
    0.48
     Chwiliwch
    0.47
    liceerd
    0.46
     kaarangay
    0.46
    verifyException
    0.45
    @[+][
    0.44
    Activations Density 0.441%

    No Known Activations