© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8955
    Prev
    Next
    INDEX
    Explanations

    references to secrets and secrecy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyExc
    -0.91
     становника
    -0.84
    MigrationBuilder
    -0.81
     GetEnumerator
    -0.80
    帖最后由
    -0.80
     surla
    -0.80
    paravant
    -0.77
     defaultstate
    -0.74
    harusnya
    -0.71
    
    -0.71
    POSITIVE LOGITS
     secret
    3.66
     Secret
    3.39
    secret
    3.33
    Secret
    3.31
     SECRET
    3.06
     secrets
    2.87
     Secrets
    2.59
    SECRET
    2.57
    secrets
    2.42
    Secrets
    2.35
    Activations Density 0.060%

    No Known Activations