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. 3-GEMMASCOPE-RES-16K
    6. 6294
    Prev
    Next
    INDEX
    Explanations

    terms related to protection and safety

    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
     Jamb
    -0.68
    MERCE
    -0.60
    onucleotide
    -0.57
     Tumble
    -0.57
    quelize
    -0.56
     AFFAIRS
    -0.56
     Ayer
    -0.55
    WillAppear
    -0.54
     CommonModule
    -0.54
     Wiring
    -0.53
    POSITIVE LOGITS
     protection
    3.07
     Protection
    2.88
     protect
    2.77
    Protection
    2.71
     Protect
    2.69
    protection
    2.68
     PROTECTION
    2.65
     protects
    2.64
     protecting
    2.63
    Protect
    2.63
    Activations Density 0.059%

    No Known Activations