© 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. 2333
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of data or data structures

    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
    ments
    -0.75
    ment
    -0.66
    WebServlet
    -0.62
    AddTagHelper
    -0.60
    WriteTagHelper
    -0.59
    contentLoaded
    -0.58
    bcryptjs
    -0.57
     Савезне
    -0.56
    +#+
    -0.56
    tal
    -0.55
    POSITIVE LOGITS
    structures
    0.77
    structure
    0.65
    points
    0.63
    stores
    0.63
    ils
    0.61
    store
    0.58
    stream
    0.57
    streams
    0.56
     Structures
    0.55
     science
    0.55
    Activations Density 0.132%

    No Known Activations