Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9117
    Prev
    Next
    INDEX
    Explanations

    instructions and prompts related to downloading or accessing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.88
     EconPapers
    -0.84
     فريبيس
    -0.84
    Xna
    -0.81
     समीक्षक
    -0.79
     المعيارى
    -0.78
    bootstrapcdn
    -0.76
     propOrder
    -0.73
     "..\..\..\
    -0.73
     zufolge
    -0.73
    POSITIVE LOGITS
     below
    1.18
    below
    0.86
     Below
    0.78
     bellow
    0.77
    Below
    0.74
     BELOW
    0.72
     ниже
    0.66
     poniżej
    0.60
     abaixo
    0.57
     nedan
    0.54
    Activations Density 0.155%

    No Known Activations