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. 12-GEMMASCOPE-RES-16K
    6. 9244
    Prev
    Next
    INDEX
    Explanations

    significant code structures or markers in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bayard
    -0.69
     NgModule
    -0.59
     Hage
    -0.57
    getJSONArray
    -0.55
     pener
    -0.55
    ítulo
    -0.53
    tona
    -0.53
    onucleotide
    -0.52
    Aiheesta
    -0.52
     Kurs
    -0.52
    POSITIVE LOGITS
    :]
    1.70
    :])
    1.28
    :],
    1.02
     invokingState
    0.80
    Jîn
    0.77
     nakalista
    0.76
     AssemblyVersion
    0.74
     abstrait
    0.67
     chré
    0.66
    isier
    0.66
    Activations Density 0.070%

    No Known Activations