© 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. 7504
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming, particularly in the context of graphical user interfaces and object-oriented programming

    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
    ReusableCell
    -0.63
    MemoryWarning
    -0.62
    aronder
    -0.55
    IsMutable
    -0.52
     combineReducers
    -0.51
    immel
    -0.50
     محفوظة
    -0.50
    tagHelperRunner
    -0.47
     numerus
    -0.47
    AddTagHelper
    -0.47
    POSITIVE LOGITS
     position
    1.71
     Position
    1.63
    Position
    1.50
     coordinates
    1.49
     positions
    1.47
     location
    1.45
     POSITION
    1.44
    position
    1.44
     Positions
    1.34
     Location
    1.33
    Activations Density 0.678%

    No Known Activations