© 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. 0-GEMMASCOPE-RES-16K
    11. 5504
    Prev
    Next
    INDEX
    Explanations

    the prefix "de-" indicating a process of removal or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -1.40
     vectorielle
    -1.31
     démocr
    -1.27
     vectorielles
    -1.27
     feroit
    -1.26
     Económica
    -1.24
     itſelf
    -1.22
     fédé
    -1.22
     financières
    -1.20
     énergé
    -1.19
    POSITIVE LOGITS
     de
    3.86
     De
    2.47
    De
    2.00
     де
    1.97
    de
    1.97
     DE
    1.85
     des
    1.34
     del
    1.20
    デ
    1.12
    DE
    1.05
    Activations Density 0.172%

    No Known Activations