© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 16328
    Prev
    Next
    INDEX
    Explanations

    instances of a certain formatting or structural element in text, particularly the beginning and end markers in a document

    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
    RenderAtEndOf
    -0.76
    Hozzáférés
    -0.74
    Personendaten
    -0.71
    Посилання
    -0.70
     متعلقه
    -0.69
     ModelExpression
    -0.69
    PutMapping
    -0.66
    достатки
    -0.66
    Filmographie
    -0.65
    ORPG
    -0.65
    POSITIVE LOGITS
     associated
    0.47
     anzu
    0.46
    JspWriter
    0.45
     ügy
    0.44
     automatiques
    0.43
     etching
    0.43
     financières
    0.43
    قایناق‌لار
    0.43
    jenih
    0.42
     Spreading
    0.42
    Activations Density 0.008%

    No Known Activations