© 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. 22-GEMMASCOPE-RES-16K
    11. 3894
    Prev
    Next
    INDEX
    Explanations

    structured data and programming constructs related to API interactions

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

    Code, filenames, and programming terms

    np_acts-logits-general · gemini-2.0-flash

    scientific and english words

    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
    Vidite
    -0.86
    NameInMap
    -0.72
    /*
    -0.71
     OFDb
    -0.65
    URLException
    -0.63
    ="#"><
    -0.62
    RegistryLite
    -0.61
    ItemBackground
    -0.61
    Personendaten
    -0.60
     Roskov
    -0.60
    POSITIVE LOGITS
    \{\\
    0.46
     Schild
    0.43
    ulemon
    0.43
    phin
    0.43
    ებ
    0.42
    Dữ
    0.42
    atalos
    0.41
    اعمال
    0.40
    NewUrlParser
    0.40
    ]<=
    0.40
    Activations Density 0.675%

    No Known Activations