Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4223
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of discomfort and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "feel" followed by an emotion/sensation

    np_acts-logits-general · gemini-2.0-flash

    comfortable feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.65
    참고
    -0.62
    jewództ
    -0.56
    ########.
    -0.54
     referenties
    -0.51
     cyclones
    -0.50
    parsedMessage
    -0.50
     Saga
    -0.49
     везе
    -0.49
     empresarial
    -0.49
    POSITIVE LOGITS
     comfort
    2.06
     comfortable
    2.04
     Comfort
    1.76
    comfort
    1.76
     COMFORT
    1.72
    Comfort
    1.72
     Comfortable
    1.69
    comfortable
    1.68
     comfor
    1.61
    Comfortable
    1.59
    Activations Density 0.138%

    No Known Activations