© 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. 9059
    Prev
    Next
    INDEX
    Explanations

    phrases relating to concepts and ideas

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

    "idea"

    np_acts-logits-general · gemini-2.0-flash

    explaining an idea

    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
    yam
    -0.61
    s
    -0.59
    </em>
    -0.55
    ன்ன
    -0.53
    cc
    -0.50
    englisch
    -0.50
    quiv
    -0.49
    ç
    -0.49
    ra
    -0.49
    tin
    -0.48
    POSITIVE LOGITS
     IDEA
    1.29
    Idea
    1.22
     ideas
    1.22
    Ideas
    1.21
     Ideas
    1.20
     IDEAS
    1.14
    ideas
    1.14
     Idea
    1.11
    IDEA
    0.99
     inappropriés
    0.92
    Activations Density 0.055%

    No Known Activations