© 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. 9263
    Prev
    Next
    INDEX
    Explanations

    special formatting characters or symbols that indicate sections or headings in a text

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

    Followed by question words

    np_acts-logits-general · gemini-2.0-flash

    question words and structural elements

    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
     lateinit
    -0.67
    Kaieteur
    -0.62
    échal
    -0.60
    MockBean
    -0.58
    Vezi
    -0.58
    Życiorys
    -0.56
    eterangan
    -0.55
    averaged
    -0.54
     Cytometry
    -0.54
    CascadeType
    -0.54
    POSITIVE LOGITS
    What
    0.84
    Why
    0.82
     What
    0.79
     Why
    0.77
     disambiguazione
    0.76
     why
    0.75
    )");
    0.75
    ")]
    0.75
     what
    0.74
    How
    0.73
    Activations Density 0.133%

    No Known Activations