© 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. 8-GEMMASCOPE-RES-16K
    6. 9737
    Prev
    Next
    INDEX
    Explanations

    administrative notices and legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -1.05
    MigrationBuilder
    -1.03
    twimg
    -1.03
     تضيفلها
    -1.02
     незавершена
    -0.99
     <=",
    -0.99
    mybatisplus
    -0.95
     BoxFit
    -0.94
    ArrowToggle
    -0.92
     дописавши
    -0.92
    POSITIVE LOGITS
    「
    0.44
    ,
    0.36
    Edit
    0.36
    equalsIgnoreCase
    0.35
     Ly
    0.34
    .
    0.34
    ként
    0.33
    《
    0.32
     ут
    0.32
    Ly
    0.32
    Activations Density 1.633%

    No Known Activations