Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15501
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to encryption algorithms and cryptography

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

    Terms related to encryption and cryptography

    np_acts-logits-general · gemini-2.0-flash

    symmetric encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    hringer
    -0.48
     externi
    -0.48
    ScopeManager
    -0.44
     paž
    -0.44
     Lordships
    -0.43
     esternos
    -0.41
     отме
    -0.40
     répondu
    -0.40
    vericks
    -0.40
    Kuch
    -0.40
    POSITIVE LOGITS
     encryption
    1.56
     encrypt
    1.34
     encrypted
    1.33
     Encryption
    1.31
     cryptography
    1.26
     cipher
    1.24
     decryption
    1.11
     Encrypt
    1.09
     Crypto
    1.08
    cipher
    1.07
    Activations Density 0.418%

    No Known Activations