© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3117
    Prev
    Next
    INDEX
    Explanations

    concepts related to digital signatures and encryption

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

    Terms related to encryption

    np_acts-logits-general · gemini-2.0-flash

    encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.48
     reicht
    -0.39
     للاسماء
    -0.37
    égalité
    -0.34
     jurídica
    -0.33
    attuale
    -0.33
     democrática
    -0.33
     mecánica
    -0.32
     situazione
    -0.32
     contemporánea
    -0.31
    POSITIVE LOGITS
    bcryptjs
    0.93
     encrypt
    0.85
     encryption
    0.82
    Encrypt
    0.82
     Encryption
    0.80
     encrypted
    0.80
    encrypt
    0.78
    encrypted
    0.76
     Encrypt
    0.74
    encryption
    0.73
    Activations Density 0.402%

    No Known Activations