© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    discussions around beliefs, values, and their implications in relationships and personal choices

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

    Follows "about," "than," or "just."

    np_acts-logits-general · gemini-2.0-flash

    explaining what something is about

    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
    scriptcase
    -0.61
     muualla
    -0.50
     Typical
    -0.50
     worsen
    -0.49
    ಾಗಿ
    -0.47
     annexed
    -0.47
    tomia
    -0.47
    themselves
    -0.46
    Abit
    -0.45
    ForValue
    -0.45
    POSITIVE LOGITS
     finding
    1.11
     knowing
    1.05
     having
    1.02
     getting
    1.00
    finding
    0.88
    knowing
    0.87
     figuring
    0.85
     keeping
    0.85
     discovering
    0.83
     ensuring
    0.83
    Activations Density 0.235%

    No Known Activations