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. 10042
    Prev
    Next
    INDEX
    Explanations

    control flow statements and the structure of code

    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
     htons
    -0.84
     purpoſe
    -0.74
     Monfieur
    -0.71
     perfons
    -0.71
     pleaſure
    -0.69
     leaſt
    -0.68
    DoubleQuotes
    -0.68
     chofe
    -0.65
     houſe
    -0.65
     doInBackground
    -0.64
    POSITIVE LOGITS
    MLLoader
    0.55
    发表于
    0.52
    ieniu
    0.51
     Beyer
    0.51
    throw
    0.50
    jupiter
    0.49
    annu
    0.48
    zahlt
    0.47
    “
    0.47
    ummer
    0.47
    Activations Density 0.055%

    No Known Activations