© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1305
    Prev
    Next
    INDEX
    Explanations

    references to display technologies and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.75
     autorytatywna
    -0.58
    Autoritní
    -0.57
     Normdatei
    -0.57
    новниш
    -0.56
    Cyfarwyddwr
    -0.55
    رشف
    -0.54
    ANDUM
    -0.53
    OGND
    -0.52
    XmlAttribute
    -0.51
    POSITIVE LOGITS
     screen
    2.74
    screen
    2.26
     screens
    2.25
     Screen
    2.10
     SCREEN
    2.07
    Screen
    2.00
    creen
    1.91
     Screens
    1.90
     pantalla
    1.88
    SCREEN
    1.82
    Activations Density 0.328%

    No Known Activations