© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4793
    Prev
    Next
    INDEX
    Explanations

    elements related to the manner in which actions are performed or described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MultipartFile
    -0.42
     NUnit
    -0.41
    addContainerGap
    -0.41
     voordeel
    -0.41
    WebVitals
    -0.40
    moveToFirst
    -0.39
     penting
    -0.39
    FieldNumber
    -0.39
     wyłą
    -0.38
    Πηγές
    -0.38
    POSITIVE LOGITS
     manner
    0.83
    manner
    0.81
     way
    0.81
    posób
    0.71
     manière
    0.70
     Manner
    0.68
     façon
    0.67
     manières
    0.64
     manier
    0.62
    نحوه
    0.60
    Activations Density 0.368%

    No Known Activations