© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4806
    Prev
    Next
    INDEX
    Explanations

    references to software updates and version changes

    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
    Personendaten
    -0.72
    iverr
    -0.67
     Khur
    -0.62
     Gim
    -0.59
    sendFile
    -0.59
    s
    -0.59
    InitStructure
    -0.59
     Cors
    -0.58
     Geh
    -0.58
    avocat
    -0.58
    POSITIVE LOGITS
     updater
    1.34
     Updates
    1.31
     Update
    1.29
     UPD
    1.26
     update
    1.25
     updates
    1.24
    updates
    1.23
     UPDATE
    1.21
    onUpdate
    1.20
    Updates
    1.20
    Activations Density 0.055%

    No Known Activations