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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6221
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handling
    -0.55
    écnicas
    -0.52
     handling
    -0.51
    似的
    -0.50
     ]
    
    -0.47
    ngdoc
    -0.46
     ради
    -0.46
    RenderAtEndOf
    -0.46
     period
    -0.46
    iense
    -0.46
    POSITIVE LOGITS
     predeceased
    0.94
    исленность
    0.66
    makeConstraints
    0.65
     löytyy
    0.64
     lovingly
    0.60
     auprès
    0.59
    stretchr
    0.58
    ulfide
    0.58
     acompañada
    0.57
    iedene
    0.56
    Activations Density 0.014%

    No Known Activations