© 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. 6-GEMMASCOPE-RES-16K
    11. 6367
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or positive emotions, particularly smiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useRef
    -0.66
    jsdelivr
    -0.66
    enderror
    -0.60
    حياته
    -0.58
    vener
    -0.57
    Beskrivning
    -0.57
     near
    -0.57
     baja
    -0.56
     me
    -0.55
     Vass
    -0.54
    POSITIVE LOGITS
     smile
    2.14
     smiles
    1.93
     Smile
    1.89
    Smile
    1.83
     smiling
    1.73
    smile
    1.69
     smiled
    1.68
     Smiling
    1.65
     Smiles
    1.63
    Smiling
    1.47
    Activations Density 0.032%

    No Known Activations