© 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. 11-GEMMASCOPE-RES-16K
    11. 9554
    Prev
    Next
    INDEX
    Explanations

    criteria related to psychological distress and overall well-being

    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
    afficheront
    -0.60
    StoryboardSegue
    -0.57
     surla
    -0.51
     ModelRenderer
    -0.49
    хьтан
    -0.48
     ProtoMessage
    -0.46
    DeleteBehavior
    -0.46
     Numerade
    -0.45
    arrings
    -0.44
    PerformLayout
    -0.44
    POSITIVE LOGITS
    LEIA
    0.34
    numerusform
    0.33
     embreagem
    0.32
    stuk
    0.32
    VU
    0.32
    endpush
    0.32
     ausz
    0.31
    rick
    0.31
    transQ
    0.31
    </>
    0.31
    Activations Density 1.450%

    No Known Activations