© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    references to culinary discussions and cultural significance

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

    "Natural" or "logical" continuations

    np_acts-logits-general · gemini-2.0-flash

    only normal or natural

    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
     totiž
    -0.49
     nemlig
    -0.45
     nämlich
    -0.45
    FromString
    -0.45
     polega
    -0.44
    じゃなくて
    -0.44
    ernalia
    -0.44
     arrep
    -0.43
     angew
    -0.43
    flashdata
    -0.42
    POSITIVE LOGITS
     naturally
    2.34
     natural
    2.13
    naturally
    2.05
     Naturally
    1.97
    natural
    1.94
     naturale
    1.87
    Natural
    1.85
    Naturally
    1.84
     naturellement
    1.84
     naturalmente
    1.80
    Activations Density 0.497%

    No Known Activations