© 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. 15-GEMMASCOPE-RES-16K
    11. 5266
    Prev
    Next
    INDEX
    Explanations

    elements of supernatural or mystical transformation and the impact of these changes on characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     senador
    -0.47
    :+:
    -0.45
     alturas
    -0.45
    aggiare
    -0.44
     autorité
    -0.44
    genodigd
    -0.44
     sagrado
    -0.43
     autonomie
    -0.43
     autrefois
    -0.43
     سكانية
    -0.43
    POSITIVE LOGITS
    EndContext
    0.75
     OFDb
    0.47
    ViewImports
    0.42
     therefor
    0.38
     thither
    0.38
     ModelRenderer
    0.37
    AccessorTable
    0.37
    IsMutable
    0.35
    WireFormatLite
    0.35
    wts
    0.35
    Activations Density 0.526%

    No Known Activations