© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14-GEMMASCOPE-RES-16K
    11. 8525
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and references to patents or legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jspb
    -0.56
    +#+
    -0.52
     AssemblyCulture
    -0.50
    styleType
    -0.46
    tagHelperRunner
    -0.46
    adaptiveStyles
    -0.45
     MainAxisSize
    -0.44
    iNdEx
    -0.43
     bParam
    -0.42
    estacks
    -0.41
    POSITIVE LOGITS
     esternos
    0.48
     CURIAM
    0.47
    ActionPerformed
    0.47
     дух
    0.45
     Odys
    0.45
     Suara
    0.45
    oramic
    0.44
     cadre
    0.44
    vul
    0.43
     års
    0.43
    Activations Density 0.388%

    No Known Activations