© 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. 28-GEMMASCOPE-RES-16K
    11. 10086
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to reversal or inverse relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "reverse" or "inverse" relationships

    np_acts-logits-general · gemini-2.0-flash

    inverse, reverse, reciprocal relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.67
    fjspx
    -0.65
    /**
    -0.51
     vastaan
    -0.50
     hyö
    -0.49
     fédé
    -0.47
    tanleria
    -0.47
     académica
    -0.47
     Económica
    -0.47
    principalColumn
    -0.46
    POSITIVE LOGITS
     reverse
    0.78
     Reverse
    0.73
     invert
    0.70
     reverses
    0.66
     flip
    0.66
     inverse
    0.65
    reverse
    0.64
     reversed
    0.64
     reversal
    0.64
     Flip
    0.63
    Activations Density 0.416%

    No Known Activations