© 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. 15621
    Prev
    Next
    INDEX
    Explanations

    specific terms related to health and medical conditions or treatments

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

    technical and research-related terminology across various domains (medical research, educational policy, technology, etc.).

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

    negative consequences or serious problems resulting from situations or actions.

    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
    性和
    -0.96
    并且
    -0.93
     והוא
    -0.92
     And
    -0.90
    力和
    -0.88
    이고
    -0.86
    子和
    -0.84
     iar
    -0.81
    ようで
    -0.81
    而且
    -0.79
    POSITIVE LOGITS
     či
    0.50
     sebagainya
    0.47
     therefrom
    0.47
     maupun
    0.47
     accordingly
    0.44
     lẫn
    0.41
     thereafter
    0.41
    bilirsiniz
    0.38
     snippetHide
    0.37
    /
    0.37
    Activations Density 1.336%

    No Known Activations