© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3046
    Prev
    Next
    INDEX
    Explanations

    terms related to flat or level surfaces and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.66
     متعلقه
    -0.58
     vong
    -0.57
    UPAC
    -0.53
    cookieParser
    -0.53
    xodo
    -0.50
     MediatR
    -0.49
    tagHelperRunner
    -0.49
     Exact
    -0.49
    exact
    -0.49
    POSITIVE LOGITS
    ness
    0.95
    NESS
    0.78
    tened
    0.72
    tener
    0.69
    tens
    0.66
    ENING
    0.65
    ening
    0.63
    DeleteBehavior
    0.62
    ly
    0.61
    tening
    0.61
    Activations Density 0.220%

    No Known Activations