© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 191
    Prev
    Next
    INDEX
    Explanations

    variables and data structures 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
     or
    -0.53
    <eos>
    -0.52
     and
    -0.50
     
    -0.49
    ,
    -0.49
     dan
    -0.49
     of
    -0.48
     pin
    -0.45
    <strong>
    -0.45
     sp
    -0.44
    POSITIVE LOGITS
     nakalista
    0.84
     فريبيس
    0.84
     myſelf
    0.83
     ſeveral
    0.82
     Efq
    0.81
    RegistryLite
    0.79
    =$?
    0.77
     himſelf
    0.77
    󠁮
    0.76
    DoubleQuotes
    0.75
    Activations Density 0.353%

    No Known Activations