© 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 EvalsExportsAPI 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. 2984
    Prev
    Next
    INDEX
    Explanations

    the concept of "reversal" or processes that involve reversing

    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
    новништво
    -0.43
     présidenti
    -0.42
    IBOutlet
    -0.42
     ceilings
    -0.42
     שוליים
    -0.41
     McGuire
    -0.41
     мѣ
    -0.41
     desic
    -0.41
     Flä
    -0.40
    Bowl
    -0.40
    POSITIVE LOGITS
     reverse
    2.95
     Reverse
    2.61
    reverse
    2.56
    Reverse
    2.45
     reversed
    2.19
     opposite
    2.09
     reverses
    2.06
     reversing
    1.95
    opposite
    1.84
     Opposite
    1.76
    Activations Density 0.150%

    No Known Activations