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

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 9327
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences and reflections

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

    preceding "was" or "had"

    np_acts-logits-general · gemini-2.0-flash

    past tense descriptions of events and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     will
    -0.54
     છે
    -0.54
     are
    -0.52
     bisher
    -0.51
     bislang
    -0.50
    จะ
    -0.48
    currently
    -0.47
    டுக
    -0.45
     agora
    -0.45
     ainfi
    -0.45
    POSITIVE LOGITS
     was
    1.55
     did
    1.03
     had
    1.01
     were
    1.00
     wasn
    0.98
     lacked
    0.98
     gave
    0.97
     took
    0.96
     didn
    0.95
     vardı
    0.94
    Activations Density 1.655%

    No Known Activations