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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15722
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "Collect" followed by "the terms in" which signals a focus on collecting or categorizing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    println
    -0.45
    polated
    -0.44
    ellini
    -0.43
     module
    -0.43
     ویکی‌پدیا
    -0.42
     Second
    -0.41
    ini
    -0.40
     –
    -0.40
    发表于
    -0.40
     Ein
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.88
    GraphicsUnit
    0.87
     חיצוניים
    0.77
    
    0.77
    matchCondition
    0.76
     extérieure
    0.75
     оригіналу
    0.71
    styleType
    0.69
     BrowserModule
    0.69
    IntoConstraints
    0.68
    Activations Density 0.221%

    No Known Activations