© 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. 17-GEMMASCOPE-RES-16K
    11. 497
    Prev
    Next
    INDEX
    Explanations

    options and solutions related to problem-solving and alternatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.79
    IsPostBack
    -0.69
    detectChanges
    -0.69
    webElementXpaths
    -0.68
    ])):
    -0.67
    bibinfo
    -0.67
    numerusform
    -0.67
    TagMode
    -0.65
    ViewFeatures
    -0.64
    writeFieldEnd
    -0.64
    POSITIVE LOGITS
     for
    0.64
     exists
    0.60
     available
    0.58
     StringTokenizer
    0.55
     solutions
    0.55
     exist
    0.55
     solution
    0.54
     viable
    0.54
     alternatives
    0.50
     POSS
    0.49
    Activations Density 0.339%

    No Known Activations