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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8753
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "protected" and related method definitions in code snippets

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

    "protected" keyword followed by "void"

    np_acts-logits-general · gemini-2.0-flash

    protected method or property

    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
     Somer
    -0.76
     Jamb
    -0.76
    脚注の使い方
    -0.73
     Gente
    -0.73
     Tumble
    -0.67
    ι
    -0.66
    timestamps
    -0.65
    Gente
    -0.64
     Vap
    -0.63
     morm
    -0.63
    POSITIVE LOGITS
     propOrder
    1.18
    protected
    1.13
     PROTECT
    0.95
    PROTECT
    0.89
     saites
    0.83
     protection
    0.83
     Protection
    0.82
     protections
    0.81
     PROTECTION
    0.80
    Protect
    0.79
    Activations Density 0.066%

    No Known Activations