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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 3208
    Prev
    Next
    INDEX
    Explanations

    sections of code related to licensing and copyright information

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

    Code and markup separators

    np_acts-logits-general · gemini-2.0-flash

    **************** separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -1.04
     الرياضيه
    -1.01
    Personendaten
    -1.00
    IUrlHelper
    -1.00
    UserScript
    -0.98
    Personensuche
    -0.94
    XmlAccessorType
    -0.88
    PreferredItem
    -0.88
     estekak
    -0.87
     Italijanski
    -0.87
    POSITIVE LOGITS
     contrário
    0.54
    uate
    0.51
    getRoot
    0.49
    ั่ง
    0.47
    tuar
    0.46
    OrEmpty
    0.46
    φέρ
    0.45
    orre
    0.45
    jot
    0.45
    mented
    0.44
    Activations Density 0.670%

    No Known Activations