© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 27-GEMMASCOPE-RES-16K
    11. 8667
    Prev
    Next
    INDEX
    Explanations

    references to the current state or availability of specific subjects, including conditions, industries, or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     künftig
    -0.45
     eventually
    -0.44
     pozdě
    -0.43
     earlier
    -0.43
     previous
    -0.43
     previously
    -0.41
     longtemps
    -0.41
     sooner
    -0.40
     zuvor
    -0.40
    后来
    -0.40
    POSITIVE LOGITS
     Currently
    0.69
    Currently
    0.68
     currently
    0.68
     Current
    0.65
     đang
    0.64
    currently
    0.64
     sedang
    0.63
     Presently
    0.63
     actualidad
    0.62
    为止
    0.62
    Activations Density 0.189%

    No Known Activations