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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 14137
    Prev
    Next
    INDEX
    Explanations

    computer programming structures and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.84
    Parcelize
    -0.76
    enumi
    -0.75
     geox
    -0.74
    DoubleQuotes
    -0.73
     esternos
    -0.73
    UrlResolution
    -0.73
    istoitu
    -0.72
    GOTREF
    -0.72
    TintMode
    -0.71
    POSITIVE LOGITS
    Diwedd
    0.41
     resulta
    0.40
    ரிய
    0.39
     calle
    0.38
    arcoma
    0.38
     kesempatan
    0.37
     cel
    0.37
    ...
    0.37
     sav
    0.37
     resourceCulture
    0.37
    Activations Density 0.567%

    No Known Activations