© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8250
    Prev
    Next
    INDEX
    Explanations

    quantitative measures related to energy efficiency and environmental impact

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

    preceding "of" or "on"

    np_acts-logits-general · gemini-2.0-flash

    GenericTest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.46
    BufferException
    -0.44
     CreateTagHelper
    -0.42
    SharedCtor
    -0.38
     McCulloch
    -0.36
    contentLoaded
    -0.35
    章节错误
    -0.34
    }});
    -0.33
    EXTENSION
    -0.33
     useSelector
    -0.32
    POSITIVE LOGITS
    Билгалдахарш
    0.50
    ագրություններ
    0.50
    KommentareTeilen
    0.48
     myſelf
    0.47
    pexpr
    0.46
     ***!
    0.46
    majánló
    0.45
    ſelves
    0.45
     chofe
    0.44
    fillType
    0.44
    Activations Density 0.221%

    No Known Activations