© 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. 25-GEMMASCOPE-RES-16K
    11. 880
    Prev
    Next
    INDEX
    Explanations

    content related to laws, regulations, and formal designations concerning health, safety, or military matters

    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
    ########.
    -0.75
     defStyleAttr
    -0.60
    CloseOperation
    -0.59
     autorytatywna
    -0.57
     CURIAM
    -0.56
    AlterField
    -0.54
    PerformLayout
    -0.52
    Diweddarwch
    -0.51
    QMetaType
    -0.51
    Hentet
    -0.50
    POSITIVE LOGITS
     use
    2.89
     usage
    2.88
     Use
    2.60
     uses
    2.56
     Usage
    2.47
    Use
    2.45
    use
    2.44
     Uses
    2.37
     USE
    2.32
     usages
    2.29
    Activations Density 0.923%

    No Known Activations