© 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. 9124
    Prev
    Next
    INDEX
    Explanations

    references to connections, relationships, or interactions among multiple items or concepts

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

    "and other" phrases

    np_acts-logits-general · gemini-2.0-flash

    and other

    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
    WebElementEntity
    -0.67
     kasarigan
    -0.48
    Демографія
    -0.47
     himo
    -0.46
    argli
    -0.46
     OFDb
    -0.45
    formazione
    -0.45
    vician
    -0.45
    Życiorys
    -0.43
     semula
    -0.43
    POSITIVE LOGITS
     other
    3.43
    other
    2.85
     autres
    2.59
    Other
    2.49
     Other
    2.47
     otros
    2.43
     otras
    2.40
    autres
    2.37
     outras
    2.31
     outros
    2.27
    Activations Density 0.351%

    No Known Activations