© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7488
    Prev
    Next
    INDEX
    Explanations

    quantitative measures and spatial parameters related to ecological studies or environmental assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    domada
    -0.30
     milliers
    -0.28
     amp
    -0.28
    ➟
    -0.27
     Expert
    -0.27
     stali
    -0.26
     Intestinal
    -0.25
     zdan
    -0.25
     Amp
    -0.25
     anhydride
    -0.24
    POSITIVE LOGITS
    featureID
    0.68
    principalColumn
    0.63
     vicinity
    0.62
    AsStream
    0.60
    aspectj
    0.57
    RegressionTest
    0.56
     proximity
    0.55
    blurRadius
    0.54
     везе
    0.54
     Conſ
    0.54
    Activations Density 1.178%

    No Known Activations