© 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. 5561
    Prev
    Next
    INDEX
    Explanations

    references to research methods and the results of scientific studies

    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
    /*
    -0.60
    enumi
    -0.56
     Humanos
    -0.53
    mybatisplus
    -0.51
    PhysRevLett
    -0.51
    LayoutStyle
    -0.49
    bukkit
    -0.49
    ={({
    -0.47
     joc
    -0.47
    gham
    -0.46
    POSITIVE LOGITS
     performed
    1.95
     perform
    1.95
     performing
    1.82
     performs
    1.80
    Perform
    1.71
     conduct
    1.70
     Perform
    1.69
     carried
    1.69
     conducted
    1.69
    perform
    1.65
    Activations Density 0.817%

    No Known Activations