© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing hyperbolic or exaggerated statements

    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
    سكري
    -0.54
    rables
    -0.51
    usercontent
    -0.49
    ながらも
    -0.49
    InitVars
    -0.47
    Patches
    -0.47
     Carsten
    -0.47
    JspWriter
    -0.46
     Descartes
    -0.46
     territory
    -0.46
    POSITIVE LOGITS
     truly
    0.87
     litté
    0.81
    truly
    0.80
     literally
    0.79
    Truly
    0.79
     Truly
    0.78
     literal
    0.78
    Literally
    0.78
     Literally
    0.73
    literally
    0.73
    Activations Density 0.081%

    No Known Activations