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. 18-GEMMASCOPE-RES-16K
    6. 10265
    Prev
    Next
    INDEX
    Explanations

    the presence of special characters and symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaços
    -0.58
     kasarigan
    -0.56
    riwal
    -0.56
     Remarque
    -0.55
    Aiheesta
    -0.50
     võimal
    -0.49
     coleção
    -0.49
     henkil
    -0.47
    исленность
    -0.47
     termica
    -0.47
    POSITIVE LOGITS
     Photocase
    0.68
    httphttps
    0.64
    expandindo
    0.60
     EventArgs
    0.58
    ItemBackground
    0.55
    tvguidetime
    0.53
    <thead>
    0.53
    intios
    0.52
     Wikipedia
    0.51
    </td>
    0.51
    Activations Density 0.091%

    No Known Activations