© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 934
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or critical aspects related to environmental science and health

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "is" followed by importance/criticality

    np_acts-logits-general · gemini-2.0-flash

    importance and criticality

    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
    Negative Logits
     löytyy
    -0.48
    antaranya
    -0.44
     Efq
    -0.43
     Monfieur
    -0.40
     équilibr
    -0.40
     suaminya
    -0.40
     potrebbero
    -0.39
    Ikus
    -0.39
     Perſ
    -0.38
     yrity
    -0.38
    POSITIVE LOGITS
     important
    1.95
    important
    1.62
     Important
    1.55
     crucial
    1.51
    重要
    1.46
     중요
    1.44
    Important
    1.41
     importance
    1.41
     importante
    1.38
     penting
    1.38
    Activations Density 0.637%

    No Known Activations