© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 4251
    Prev
    Next
    INDEX
    Explanations

    references to mathematical proofs, theorems, and generalizations in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ணி
    -0.44
    otter
    -0.41
    تفصیلات
    -0.39
     charset
    -0.39
     forth
    -0.37
    WHE
    -0.36
    elab
    -0.36
     ند
    -0.36
    borderSide
    -0.36
    tere
    -0.36
    POSITIVE LOGITS
    Jereo
    1.19
     snippetHide
    0.99
    StructEnd
    0.87
     NSCoder
    0.85
     CreateTagHelper
    0.84
     оригіналу
    0.82
     GenerationType
    0.81
    oa̍t
    0.80
     cazul
    0.79
    colgroup
    0.78
    Activations Density 0.996%

    No Known Activations