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. 7-GEMMASCOPE-RES-16K
    6. 9143
    Prev
    Next
    INDEX
    Explanations

    instances of the word "different" and its variations, indicating a focus on diversity or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielle
    -0.94
     umana
    -0.89
     nucléaire
    -0.84
     prenez
    -0.83
     humaines
    -0.80
     sólidos
    -0.80
     humaine
    -0.79
     picioare
    -0.79
     mijne
    -0.79
     étoient
    -0.79
    POSITIVE LOGITS
     different
    1.38
    Different
    1.36
     Different
    1.29
    different
    1.24
     DIFFERENT
    1.24
     difer
    1.09
     kinds
    0.97
    不同
    0.90
     diferente
    0.89
     diff
    0.89
    Activations Density 0.086%

    No Known Activations