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. 1035
    Prev
    Next
    INDEX
    Explanations

    code-related structure and formatting elements 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
    endphp
    -1.06
     StatelessWidget
    -0.92
     ExecuteAsync
    -0.86
    endpush
    -0.84
     Paglinawan
    -0.81
     []:
    -0.81
    DebuggerNonUser
    -0.77
    EndGlobalSection
    -0.76
     autorytatywna
    -0.74
    SharedDtor
    -0.72
    POSITIVE LOGITS
     also
    0.62
     Vikipedi
    0.61
     etiam
    0.49
     deles
    0.47
     even
    0.47
     همچنین
    0.47
     Also
    0.45
     alternatively
    0.45
     purpure
    0.43
     ayrıca
    0.43
    Activations Density 0.460%

    No Known Activations