© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28172
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the act of examining or reviewing something

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

    take a look at

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    </b>
    -0.49
     
    -0.48
     Mus
    -0.46
     μ
    -0.46
     thành
    -0.46
     déb
    -0.45
     mu
    -0.44
    mu
    -0.44
    abo
    -0.44
     #
    -0.44
    POSITIVE LOGITS
    Personensuche
    1.20
    ViewFeatures
    1.13
     للاسماء
    1.03
    脚注の使い方
    1.02
     تضيفلها
    1.02
    SourceChecksum
    1.01
    NameInMap
    1.01
     '\\;'
    0.97
    сылкі
    0.96
    Tikang
    0.94
    Activations Density 0.011%

    No Known Activations