© 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. 6657
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about personal growth and experiences in life

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

    details about personal life experiences and challenges, especially related to single motherhood or learning new skills.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    descriptions of school life and learning environments, especially transitions to new grades, classes, and routines.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases describing personal experiences of learning, adjusting to, or navigating new or challenging situations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    rungsseite
    -0.54
    GEBURTSDATUM
    -0.49
     inmig
    -0.48
     MessageBoxIcon
    -0.46
     väx
    -0.44
     varandra
    -0.43
     occupa
    -0.43
    行政区划
    -0.42
    
    -0.41
     minimizes
    -0.40
    POSITIVE LOGITS
     nors
    0.44
     EconPapers
    0.43
    dafx
    0.42
    bootstrapcdn
    0.42
    تقاوى
    0.41
    IsPostBack
    0.41
    enderror
    0.40
     hur
    0.40
     Pros
    0.37
     ding
    0.37
    Activations Density 0.116%

    No Known Activations