© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8518
    Prev
    Next
    INDEX
    Explanations

    foundational concepts and their relationships within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataSetChanged
    -0.70
    readystatechange
    -0.62
    migiano
    -0.62
    toMatchSnapshot
    -0.61
    Multiline
    -0.60
     دیکھیے
    -0.59
     NgModule
    -0.58
    Tikang
    -0.58
     geda
    -0.57
    ogast
    -0.57
    POSITIVE LOGITS
     foundations
    1.24
     foundation
    1.15
     bases
    1.09
     base
    1.07
     basis
    1.05
    Bases
    1.04
     underpin
    1.01
    basis
    1.00
     fundament
    0.99
     getBase
    0.93
    Activations Density 0.293%

    No Known Activations