© 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. 3-GEMMASCOPE-RES-16K
    11. 8150
    Prev
    Next
    INDEX
    Explanations

    instances of the word "smile" and other expressions of happiness or friendliness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.61
     ab
    -0.60
     near
    -0.58
    madu
    -0.56
     pod
    -0.55
     N
    -0.55
     Ed
    -0.55
    뷔
    -0.54
     In
    -0.54
     Pod
    -0.54
    POSITIVE LOGITS
     smile
    3.11
     smiles
    2.72
     Smile
    2.64
    Smile
    2.46
    smile
    2.39
     smiling
    2.33
     smiled
    2.26
     Smiles
    2.18
     Smiling
    2.06
    smiles
    1.97
    Activations Density 0.049%

    No Known Activations