© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8930
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.85
     "));
    -0.76
    '))
    
    -0.68
     GAO
    -0.67
     firebaseConfig
    -0.66
    }`
    -0.65
     
    -0.65
     ögon
    -0.64
    "));
    
    -0.63
     visor
    -0.63
    POSITIVE LOGITS
     Instead
    1.12
    Instead
    1.05
     instead
    1.01
    instead
    0.92
     Rather
    0.86
     rather
    0.82
    Rather
    0.78
    uttosto
    0.76
     Statt
    0.72
     statt
    0.68
    Activations Density 0.148%

    No Known Activations