© 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. 23-GEMMASCOPE-RES-16K
    11. 1825
    Prev
    Next
    INDEX
    Explanations

    terminology related to procedural requirements or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.45
    Vtbl
    -0.45
    Rptr
    -0.41
    oneofs
    -0.39
    ➋
    -0.39
    olverine
    -0.38
    eckt
    -0.38
    tade
    -0.38
    StatusOK
    -0.35
    izontal
    -0.35
    POSITIVE LOGITS
     necessity
    0.77
     Necessity
    0.71
     Notwendigkeit
    0.70
     need
    0.69
     needed
    0.69
    NEED
    0.68
     necessidade
    0.66
    need
    0.66
    が必要
    0.66
    necess
    0.65
    Activations Density 0.585%

    No Known Activations