© 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. 1-GEMMASCOPE-RES-16K
    11. 15274
    Prev
    Next
    INDEX
    Explanations

    mentions of "SA" and the word "za," indicating references related to security assessments or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtre
    -0.74
     uſ
    -0.73
     ſen
    -0.72
    出版年
    -0.71
     purpoſe
    -0.67
     Reſ
    -0.66
     eksemp
    -0.65
    tinyos
    -0.65
     vĩnh
    -0.65
     Conſ
    -0.63
    POSITIVE LOGITS
     за
    1.18
     za
    1.15
    Za
    0.91
    За
    0.90
     Za
    0.89
     За
    0.83
    за
    0.67
     ЗА
    0.61
     SA
    0.59
     عن
    0.58
    Activations Density 0.013%

    No Known Activations