© 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. 6278
    Prev
    Next
    INDEX
    Explanations

    information related to reading and literature

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

    something is in progress

    np_acts-logits-general · gemini-2.0-flash

    currently happening

    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
     previous
    -0.77
     pernah
    -0.72
     Previous
    -0.71
     dann
    -0.71
     précédente
    -0.71
     later
    -0.70
     später
    -0.70
     Later
    -0.68
     Subsequent
    -0.68
     späteren
    -0.67
    POSITIVE LOGITS
     currently
    1.83
    currently
    1.70
     presently
    1.59
     Currently
    1.54
    Currently
    1.53
     actuellement
    1.50
     derzeit
    1.48
     obecnie
    1.38
     now
    1.36
     actualmente
    1.34
    Activations Density 0.535%

    No Known Activations