© 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. 3-GEMMASCOPE-RES-16K
    11. 4081
    Prev
    Next
    INDEX
    Explanations

    names and references to a specific character or entity associated with 'Sav'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rujuakan
    -0.56
    ритори
    -0.51
    braucher
    -0.50
    
    -0.50
    цездатний
    -0.46
     yyr
    -0.46
    ViewImports
    -0.44
    enguin
    -0.44
     uLocal
    -0.44
    hdas
    -0.44
    POSITIVE LOGITS
     sav
    0.73
    addGap
    0.65
    sav
    0.62
     Sav
    0.60
    TagHelpers
    0.58
    Sav
    0.57
    AddTagHelper
    0.49
    UnitTesting
    0.49
    IBOutlet
    0.49
    Tal
    0.48
    Activations Density 1.527%

    No Known Activations