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. 20-GEMMASCOPE-RES-16K
    6. 632
    Prev
    Next
    INDEX
    Explanations

    references to activities or interests related to photography, design, or the arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.82
    AddTagHelper
    -0.75
    IndentedString
    -0.66
    httphttps
    -0.64
    MLLoader
    -0.64
    ModelSerializer
    -0.63
    __.__
    -0.60
     BoxDecoration
    -0.59
    stood
    -0.58
    ignez
    -0.57
    POSITIVE LOGITS
     wanting
    1.34
     desiring
    1.17
     wishing
    1.13
     looking
    1.10
     alike
    1.08
     interested
    1.08
     seeking
    1.02
     want
    1.00
     interesados
    0.96
     desirous
    0.96
    Activations Density 0.204%

    No Known Activations