© 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. 10589
    Prev
    Next
    INDEX
    Explanations

    various instances of the word "flip" and related terms in technical or programming contexts, particularly within code or mathematical expressions

    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
    AddTagHelper
    -0.48
     Efq
    -0.42
    tagHelperRunner
    -0.42
    Hashtag
    -0.40
    bureau
    -0.39
     Tsun
    -0.39
    Lawn
    -0.38
     @}
    -0.38
     Bureau
    -0.38
     PREF
    -0.38
    POSITIVE LOGITS
     flip
    0.81
    flip
    0.77
     flipped
    0.76
    Flip
    0.74
     Flip
    0.71
     reversal
    0.70
     reversed
    0.69
     broker
    0.68
    flipped
    0.66
    Wrapper
    0.66
    Activations Density 0.174%

    No Known Activations