© 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. 2-GEMMASCOPE-RES-16K
    11. 10589
    Prev
    Next
    INDEX
    Explanations

    terms related to flipping and inversion processes in data or imaging techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.52
    AutoScaleMode
    -0.43
    onedDateTime
    -0.42
     
    -0.41
     integr
    -0.40
     Batam
    -0.40
    AnchorTagHelper
    -0.40
     Latina
    -0.39
    匿名使用者
    -0.39
     Integral
    -0.38
    POSITIVE LOGITS
     inversion
    1.17
     invert
    1.09
     inverted
    1.05
     inver
    1.03
     flip
    1.02
     Inversion
    1.02
     reversed
    1.01
    inversion
    0.96
    flip
    0.96
    Invert
    0.95
    Activations Density 0.276%

    No Known Activations