© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 375
    Prev
    Next
    INDEX
    Explanations

    references to kidney-related health issues and symptoms

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

    detailed medical language and instructions related to medical diagnoses and treatments.

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

    words and phrases that appear in imperative or instructional sentences, particularly those directing the reader to take action or seek information.

    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
    Jeografia
    -0.59
    ImageContext
    -0.58
     informée
    -0.53
     հղումներ
    -0.53
     Paglinawan
    -0.52
    oa̍t
    -0.52
     שוליים
    -0.51
    fillType
    -0.50
    clerosis
    -0.50
    ergies
    -0.50
    POSITIVE LOGITS
     according
    0.47
     rest
    0.40
     shall
    0.39
     detailed
    0.39
     acuerdo
    0.38
    ayos
    0.36
     appropriately
    0.36
     properly
    0.36
     entsprechend
    0.35
     Try
    0.35
    Activations Density 0.118%

    No Known Activations