© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15905
    Prev
    Next
    INDEX
    Explanations

    terms related to trust and authenticity in online communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.60
     '\\;'
    -0.57
    himovic
    -0.54
     Censo
    -0.50
    unknownFields
    -0.50
    EDEFAULT
    -0.50
     ChromeDriver
    -0.48
    InjectAttribute
    -0.48
     Chaplain
    -0.48
     Viel
    -0.47
    POSITIVE LOGITS
     trustworthy
    1.15
     trustworthiness
    1.05
     credibility
    0.94
     trust
    0.94
     trusted
    0.90
     credible
    0.90
     reputable
    0.88
     TRUST
    0.84
     reliability
    0.83
    trust
    0.82
    Activations Density 0.228%

    No Known Activations