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. 10440
    Prev
    Next
    INDEX
    Explanations

    elements related to JSON data structures and API interaction

    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
     initComponents
    -0.90
    httphttps
    -0.81
     kasarigan
    -0.80
    ($__
    -0.69
     Administrativna
    -0.67
    లాలు
    -0.66
    +#+
    -0.63
     Hima
    -0.61
     يتيمه
    -0.61
    évaluateur
    -0.60
    POSITIVE LOGITS
     JSON
    1.74
    JSON
    1.58
     json
    1.57
    json
    1.39
    Json
    1.35
     Json
    1.29
    Gson
    1.00
     JSONObject
    0.95
    FromJson
    0.94
    JSONObject
    0.94
    Activations Density 0.386%

    No Known Activations