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. 15-GEMMASCOPE-RES-16K
    6. 2140
    Prev
    Next
    INDEX
    Explanations

    expressions of understanding and empathy towards others' perspectives and feelings

    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
    #
    -0.60
     LUMP
    -0.54
     fortune
    -0.54
    Pyx
    -0.54
    ⓧ
    -0.52
    -(-
    -0.52
     BoxDecoration
    -0.52
    terre
    -0.51
     Curs
    -0.51
    webElement
    -0.50
    POSITIVE LOGITS
    featureID
    0.76
     appreciate
    0.71
     appreciates
    0.69
    BeginInit
    0.66
     understand
    0.64
    Understand
    0.63
     Understand
    0.62
    understand
    0.61
     understands
    0.61
     protesta
    0.61
    Activations Density 0.164%

    No Known Activations