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. 6-GEMMASCOPE-RES-16K
    6. 12135
    Prev
    Next
    INDEX
    Explanations

    structural or organizational patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.92
    AsUp
    -0.80
    っこう
    -0.79
     dAtA
    -0.77
    complexContent
    -0.76
    aarrggbb
    -0.71
    transQ
    -0.71
     <",
    -0.70
    SharedDtor
    -0.69
     препратки
    -0.66
    POSITIVE LOGITS
    شهاد
    0.65
    Hochspringen
    0.63
    DebuggerNonUser
    0.59
    tagHelper
    0.57
    tagHelperRunner
    0.56
     يتيمه
    0.54
    ResumeLayout
    0.54
    marginHorizontal
    0.50
    álva
    0.50
     متعلقه
    0.50
    Activations Density 0.013%

    No Known Activations