© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8259
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific processes and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UpperCase
    -0.25
     насељу
    -0.24
    ếp
    -0.22
    леко
    -0.21
     lieb
    -0.21
    ניים
    -0.20
     ujednoznacz
    -0.20
    طن
    -0.20
    toUpperCase
    -0.20
    nitzer
    -0.20
    POSITIVE LOGITS
     time
    2.53
     Time
    2.41
    Time
    2.19
     시간
    2.13
     TIME
    2.13
    时间
    2.05
    time
    2.00
    的时间
    1.98
     tijd
    1.97
     tiempo
    1.94
    Activations Density 1.629%

    No Known Activations