© 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. 9-GEMMASCOPE-RES-16K
    11. 10755
    Prev
    Next
    INDEX
    Explanations

    specific references to individuals and their associated attributes or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invitados
    -0.34
    üglich
    -0.33
     آبی
    -0.31
    اصيل
    -0.30
     remembers
    -0.29
     Infórmanos
    -0.28
    nameof
    -0.28
     grande
    -0.28
     revistas
    -0.28
    RegistryLite
    -0.28
    POSITIVE LOGITS
    PropertyChanging
    0.63
    mtrl
    0.61
    quiao
    0.60
     Minaj
    0.59
     Obama
    0.58
    MemoryWarning
    0.58
    synthesize
    0.58
     defaultstate
    0.57
    vedev
    0.57
     Kinect
    0.57
    Activations Density 1.000%

    No Known Activations