© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7866
    Prev
    Next
    INDEX
    Explanations

    instances of memory allocation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.07
    MigrationBuilder
    -1.04
    StoryboardSegue
    -0.91
     propOrder
    -0.88
    WebVitals
    -0.77
    SerializedName
    -0.76
    DataAnnotations
    -0.72
    leſs
    -0.70
     виправивши
    -0.69
     itſelf
    -0.67
    POSITIVE LOGITS
    
    1.27
    EIF
    0.80
     {//
    0.66
    bitField
    0.56
     //
    0.56
    SourceChecksum
    0.56
    #+#
    0.53
    {//
    0.52
     aload
    0.50
    ftagPool
    0.47
    Activations Density 0.043%

    No Known Activations