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. 13-GEMMASCOPE-RES-16K
    6. 13432
    Prev
    Next
    INDEX
    Explanations

    descriptors of cuteness and charm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -0.70
     ControllerBase
    -0.66
    PathVariable
    -0.60
    enderror
    -0.60
    ̍
    -0.59
    (&:
    -0.59
    bufio
    -0.58
    IsContent
    -0.58
     bodyParser
    -0.58
    bindParam
    -0.57
    POSITIVE LOGITS
     cute
    1.17
     charming
    1.13
     Cute
    1.08
     adorable
    1.07
     cutest
    1.01
    Cute
    1.00
     sweetness
    1.00
     Adorable
    0.99
     sweet
    0.99
     delightful
    0.97
    Activations Density 0.077%

    No Known Activations