© 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. 31-GEMMASCOPE-RES-16K
    11. 9806
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and their severity

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

    statistical terms and ranges in academic or research text.

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

    numerical ranges and categorical scales used in scientific and medical data classification.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.48
    yntaxException
    -0.37
    Fullscreen
    -0.34
    flashdata
    -0.33
    drag
    -0.33
     drag
    -0.32
     époux
    -0.32
     Tut
    -0.31
    Tut
    -0.31
    ╩
    -0.31
    POSITIVE LOGITS
     intermediate
    1.95
     middle
    1.81
    intermediate
    1.69
     Intermediate
    1.65
    middle
    1.60
    Intermediate
    1.60
     medium
    1.59
     mid
    1.52
     moderate
    1.42
     moderately
    1.41
    Activations Density 1.040%

    No Known Activations