© 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. 14-GEMMASCOPE-RES-16K
    11. 11794
    Prev
    Next
    INDEX
    Explanations

    references to quantities and their measurements, particularly comparisons involving doubling, tripling, and related statistical increases

    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
    
    -0.50
    addPreferredGap
    -0.43
    PreInfinity
    -0.42
    IndentedString
    -0.42
     defaultstate
    -0.41
     DialogInterface
    -0.40
    inSlope
    -0.40
    ۗ
    -0.40
     tolerably
    -0.39
    concrete
    -0.39
    POSITIVE LOGITS
     helft
    0.55
    NewUrlParser
    0.47
     AssemblyTitle
    0.47
     Half
    0.46
    一半
    0.44
     half
    0.42
    Half
    0.41
     gyhoeddwyd
    0.40
     tripled
    0.40
     halved
    0.40
    Activations Density 0.256%

    No Known Activations