© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12891
    Prev
    Next
    INDEX
    Explanations

    technical or procedural solutions to complex problems

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

    Following "to" plus a verb related to problem-solving

    np_acts-logits-general · gemini-2.0-flash

    to solve or avoid problems

    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
     nahilalakip
    -1.09
    SequentialGroup
    -0.89
     ProtoMessage
    -0.82
    OGND
    -0.79
    новниш
    -0.75
    webElementXpaths
    -0.74
     Roskov
    -0.73
    UnsafeEnabled
    -0.73
    رشف
    -0.72
    prnewswire
    -0.71
    POSITIVE LOGITS
     solution
    1.75
     Solution
    1.57
    Solution
    1.51
    solution
    1.51
     remedy
    1.46
     solutions
    1.40
     SOLUTION
    1.39
     oplossing
    1.38
     solución
    1.33
    解决方案
    1.29
    Activations Density 0.625%

    No Known Activations