© 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. 18-GEMMASCOPE-RES-16K
    11. 2206
    Prev
    Next
    INDEX
    Explanations

    phrases related to cellular and molecular mechanisms in the context of immune responses

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

    Statements that start with "We" or refer to existing data

    np_acts-logits-general · gemini-2.0-flash

    We conclude, have shown, data suggests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    روش
    -0.52
     walk
    -0.50
     Diakses
    -0.50
    Apri
    -0.48
     cammin
    -0.47
    zahn
    -0.47
    npm
    -0.46
    AMIL
    -0.46
     gummy
    -0.46
     suele
    -0.45
    POSITIVE LOGITS
    WithIOException
    0.82
    CodedInputStream
    0.76
     elegantly
    0.75
    ьаж
    0.72
    recently
    0.71
    ंदीखरीदारी
    0.69
     intrigu
    0.68
     postulated
    0.67
     récemment
    0.67
     recently
    0.64
    Activations Density 2.046%

    No Known Activations