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. 10-GEMMASCOPE-RES-16K
    6. 3127
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to XML and its schema definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.20
     autorytatywna
    -1.14
    BeginContext
    -1.13
    migrationBuilder
    -1.11
    ValueStyle
    -1.08
     defaultstate
    -1.06
     InputDecoration
    -1.00
    TagMode
    -0.98
    AndEndTag
    -0.98
     consultato
    -0.97
    POSITIVE LOGITS
    endregion
    0.96
    Sqft
    0.85
    jgl
    0.58
     jsPsych
    0.55
     ResourceManager
    0.54
    treeview
    0.54
    param
    0.52
     
    0.50
     상세
    0.49
    ult
    0.48
    Activations Density 0.008%

    No Known Activations