© 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. 11-GEMMASCOPE-RES-16K
    11. 6629
    Prev
    Next
    INDEX
    Explanations

    references to various locations or types of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kim
    -0.54
    GetNext
    -0.48
    ỳnh
    -0.47
     hydrodynamic
    -0.47
    Související
    -0.46
     hydrostatic
    -0.46
    ientras
    -0.46
     biometric
    -0.45
     Hy
    -0.45
     Khartoum
    -0.44
    POSITIVE LOGITS
    place
    1.48
     PLACE
    1.43
     place
    1.41
    Place
    1.40
    PLACE
    1.38
     Place
    1.35
    places
    1.27
    Places
    1.25
     places
    1.22
     Places
    1.21
    Activations Density 0.078%

    No Known Activations