© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8825
    Prev
    Next
    INDEX
    Explanations

    information about structures, functions, and goals of various systems or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    purpose or objectives

    np_acts-logits-general · gemini-2.0-flash

    purpose or objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.54
    ValueStyle
    -0.53
    olge
    -0.50
    الحياه
    -0.49
    disposing
    -0.46
    FromNib
    -0.44
    
    -0.43
    Kilder
    -0.42
    necedor
    -0.42
    ThroughAttribute
    -0.42
    POSITIVE LOGITS
     purpose
    1.91
     aim
    1.84
     aims
    1.65
     Purpose
    1.53
    Purpose
    1.53
    目的
    1.50
     aimed
    1.48
    目的是
    1.46
    purpose
    1.45
     aiming
    1.43
    Activations Density 0.698%

    No Known Activations