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. 21-GEMMASCOPE-RES-16K
    6. 7390
    Prev
    Next
    INDEX
    Explanations

    dialogue from characters expressing emotions and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fevere
    -0.63
     betweenstory
    -0.61
     riconoscimento
    -0.60
    odymium
    -0.60
     Saying
    -0.60
    saying
    -0.59
     Telling
    -0.59
    +#+#
    -0.58
     diciendo
    -0.57
     pauv
    -0.57
    POSITIVE LOGITS
     nud
    0.64
     patted
    0.55
    发表于
    0.54
     initComponents
    0.53
     frowned
    0.52
    migrationBuilder
    0.52
     grinned
    0.52
     push
    0.52
     shrugged
    0.52
     समीक्षक
    0.51
    Activations Density 0.066%

    No Known Activations