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. 2717
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooperation or assistance in a task

    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
    isContained
    -0.83
     Monfieur
    -0.81
     myſelf
    -0.79
     itſelf
    -0.76
    \{\\
    -0.73
     auffi
    -0.72
     himſelf
    -0.70
    elemField
    -0.69
     ***!
    -0.69
     AppColors
    -0.68
    POSITIVE LOGITS
     careful
    0.86
     cleverly
    0.77
     skillful
    0.76
     clever
    0.74
     dzięki
    0.72
     carefully
    0.72
     Careful
    0.72
     skilful
    0.70
    Dzięki
    0.66
     Carefully
    0.66
    Activations Density 0.312%

    No Known Activations