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. 16-GEMMASCOPE-RES-16K
    6. 14976
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and cryptography

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

    RSA keys, encryption, and certificates

    np_acts-logits-general · gemini-2.0-flash

    RSA public key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lencia
    -0.53
     MediatR
    -0.49
     gql
    -0.46
    ümü
    -0.46
     GreatSchools
    -0.43
     caused
    -0.41
     floor
    -0.40
     llegar
    -0.40
     dataSnapshot
    -0.39
    chandising
    -0.39
    POSITIVE LOGITS
     encryption
    0.97
     cryptographic
    0.93
     cryptography
    0.90
     encrypted
    0.87
     Secure
    0.84
     encrypt
    0.82
     secure
    0.81
     nahilalakip
    0.80
     security
    0.77
    crypto
    0.77
    Activations Density 0.597%

    No Known Activations