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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 14139
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and dates within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fattning
    -0.58
     suppresses
    -0.54
     suppress
    -0.54
    onAttach
    -0.53
    })`
    -0.52
     JAXBElement
    -0.52
     سنت
    -0.50
    writeFieldEnd
    -0.50
    
    -0.50
     repress
    -0.50
    POSITIVE LOGITS
    cshtml
    0.63
    +:+
    0.57
     etern
    0.55
    Bers
    0.55
    enumi
    0.55
    WithIOException
    0.55
    forder
    0.54
    itsub
    0.53
    /**
    0.51
     snork
    0.51
    Activations Density 0.126%

    No Known Activations