© 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. 10316
    Prev
    Next
    INDEX
    Explanations

    personal stories of health struggles and alternative treatment experiences

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

    First person pronouns and possessives

    np_acts-logits-general · gemini-2.0-flash

    personal narratives and life events

    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
    rungsseite
    -0.44
     provis
    -0.36
    обе
    -0.34
    Ligações
    -0.34
     ProtoMessage
    -0.33
     pas
    -0.32
     provision
    -0.32
     base
    -0.32
     Croce
    -0.31
    Beschreibung
    -0.31
    POSITIVE LOGITS
     CreateTagHelper
    0.71
    inSlope
    0.56
    ftagPool
    0.56
     betweenstory
    0.55
    enderror
    0.54
     cervello
    0.50
     universitaria
    0.49
    genodigd
    0.49
     underwent
    0.48
     gioielli
    0.48
    Activations Density 0.216%

    No Known Activations