© 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. 25-GEMMASCOPE-RES-16K
    6. 15114
    Prev
    Next
    INDEX
    Explanations

    references to processes or structures in technical or scientific contexts, especially involving diagrams or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    rechter
    -0.43
    genodigd
    -0.36
     zoude
    -0.35
     eſſ
    -0.33
     pipa
    -0.32
     uſe
    -0.32
     ſtre
    -0.32
     koska
    -0.31
     juſ
    -0.31
     preſent
    -0.31
    POSITIVE LOGITS
     illustrating
    0.65
     view
    0.63
     example
    0.63
     showing
    0.62
     viewed
    0.61
    :✨
    0.61
    CloseOperation
    0.59
     defaultstate
    0.58
     Example
    0.58
     typical
    0.57
    Activations Density 0.883%

    No Known Activations