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. 8-GEMMASCOPE-RES-16K
    6. 4690
    Prev
    Next
    INDEX
    Explanations

    elements related to document formatting commands

    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
    DropColumn
    -0.51
     TextAppearance
    -0.47
    yska
    -0.45
    ναι
    -0.45
     verdi
    -0.45
     Cientí
    -0.44
     Zoll
    -0.44
     plati
    -0.43
     acc
    -0.43
    Eloquent
    -0.43
    POSITIVE LOGITS
    usepackage
    1.44
    ParallelGroup
    1.32
     BorderRadius
    1.21
    gms
    0.97
    LayoutStyle
    0.96
     TextStyle
    0.92
    ValueGeneration
    0.92
     FontWeight
    0.91
     lateinit
    0.88
     pinulongan
    0.86
    Activations Density 0.010%

    No Known Activations