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. 0-GEMMASCOPE-RES-16K
    6. 9807
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "empiricism" and aspects related to beauty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -1.69
     pleaſure
    -1.61
     Houſe
    -1.61
     doubtnut
    -1.60
     itſelf
    -1.60
     myſelf
    -1.59
     ―――――
    -1.55
     Theſe
    -1.52
    ſelf
    -1.51
     ſeveral
    -1.50
    POSITIVE LOGITS
     
    0.91
     emp
    0.81
    ,
    0.80
    .
    0.77
    y
    0.71
    emp
    0.69
    h
    0.69
    ny
    0.68
    '
    0.68
     (
    0.68
    Activations Density 0.432%

    No Known Activations