© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5664
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional responses and personal feelings

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

    conversational and narrative language about personal experiences, research, or information-seeking.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    mitian
    -0.55
     cerevisiae
    -0.44
    esgue
    -0.43
     okuyayım
    -0.42
     xz
    -0.41
     bogotá
    -0.40
     Provin
    -0.40
    InSection
    -0.39
    formatics
    -0.39
     روزانه
    -0.38
    POSITIVE LOGITS
    ftagPool
    0.49
    GOTREF
    0.47
    SourceChecksum
    0.45
    QMetaType
    0.45
    ActionCreators
    0.44
     autorytatywna
    0.42
    lccn
    0.41
    ViewImports
    0.40
    archiviato
    0.40
    Personendaten
    0.39
    Activations Density 0.355%

    No Known Activations