© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5814
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to secrecy and concealment

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    MessageOf
    -0.60
    +:+
    -0.54
    脚注の使い方
    -0.54
    Autoritní
    -0.53
    }$​
    -0.51
    Brainz
    -0.49
    XMLSchema
    -0.48
    Спољашње
    -0.47
    AnimationsModule
    -0.47
     boulevard
    -0.46
    POSITIVE LOGITS
     secretly
    1.32
     secret
    1.12
     sneaking
    1.06
     sneaky
    1.04
    偷偷
    1.02
     hidden
    1.01
    secret
    0.98
     sneak
    0.98
     clandestine
    0.98
     stealth
    0.97
    Activations Density 0.317%

    No Known Activations