© 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. 7377
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems or issues that need addressing

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

    preceding a problem or issue

    np_acts-logits-general · gemini-2.0-flash

    explaining a problem

    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
    tagHelperRunner
    -0.68
     FetchType
    -0.68
    +:+
    -0.62
    出版年
    -0.59
    celotti
    -0.56
    EndContext
    -0.56
    JTable
    -0.55
     advantages
    -0.54
    balleur
    -0.54
    lück
    -0.54
    POSITIVE LOGITS
     lack
    0.83
    如何在
    0.77
    如何
    0.77
     finding
    0.74
     whether
    0.72
     how
    0.71
     getting
    0.70
     inability
    0.70
     timing
    0.68
    Getting
    0.66
    Activations Density 0.301%

    No Known Activations