© 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. 2-GEMMASCOPE-RES-16K
    11. 6195
    Prev
    Next
    INDEX
    Explanations

    words related to the Hindu deity Narasimha

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ν
    -0.45
     Ne
    -0.41
     N
    -0.40
     Ni
    -0.39
     ਨ
    -0.39
     Ни
    -0.37
     ני
    -0.37
     Nik
    -0.37
    elemField
    -0.36
    цездатний
    -0.36
    POSITIVE LOGITS
    ned
    1.23
    nan
    1.21
    nal
    1.21
    nar
    1.16
    nat
    1.14
    nos
    1.13
    nor
    1.13
    non
    1.13
    nu
    1.11
    nn
    1.10
    Activations Density 0.603%

    No Known Activations