© 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. 158
    Prev
    Next
    INDEX
    Explanations

    descriptions of emotional engagement and enthusiasm

    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
     []:
    -0.65
    HasForeignKey
    -0.65
    
    -0.62
     ComVisible
    -0.58
     AssemblyProduct
    -0.56
     halus
    -0.56
     softener
    -0.56
    roffene
    -0.54
    GEBURTSDATUM
    -0.53
    celine
    -0.53
    POSITIVE LOGITS
     energy
    1.49
     energi
    1.31
     enthusiasm
    1.30
     energ
    1.28
    energy
    1.26
     energized
    1.25
     energetic
    1.25
     excitement
    1.20
    energ
    1.19
     energía
    1.15
    Activations Density 0.386%

    No Known Activations