© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9890
    Prev
    Next
    INDEX
    Explanations

    references to differences or comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.53
    sidemargin
    -0.47
    expandindo
    -0.45
     Paglinawan
    -0.45
     AssemblyCulture
    -0.43
    ➟
    -0.42
     CreateTagHelper
    -0.41
    StructEnd
    -0.40
    userManager
    -0.40
     Hivatalos
    -0.39
    POSITIVE LOGITS
     differs
    1.08
     different
    1.02
     differ
    0.95
     Different
    0.95
     differently
    0.94
    Different
    0.90
     differed
    0.90
    different
    0.89
     berbeda
    0.85
     diferente
    0.79
    Activations Density 0.661%

    No Known Activations