© 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. 15-GEMMASCOPE-RES-16K
    11. 4928
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases and existential questions

    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
    
    -0.71
    ţilor
    -0.64
    lectricité
    -0.63
     peintures
    -0.61
     legislation
    -0.61
    мышлен
    -0.61
     pouvoirs
    -0.61
     mellitus
    -0.61
     Kleidung
    -0.60
     helft
    -0.60
    POSITIVE LOGITS
     themselves
    0.92
     are
    0.86
    wolves
    0.84
    themselves
    0.84
     yourselves
    0.83
     voltak
    0.77
     were
    0.77
    preduce
    0.76
     ARE
    0.70
    FundMe
    0.70
    Activations Density 0.508%

    No Known Activations