Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 8239
    Prev
    Next
    INDEX
    Explanations

    lines of code that include header files 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bioaccumulative
    -0.60
    kloped
    -0.58
    formik
    -0.54
     DBNull
    -0.50
    唆
    -0.49
    batim
    -0.48
    fromUtf
    -0.48
     Permalink
    -0.48
     Maldives
    -0.47
    volent
    -0.47
    POSITIVE LOGITS
    include
    3.58
     include
    1.95
    Include
    1.91
    INCLUDE
    1.82
     Include
    1.77
     INCLUDE
    1.65
     includes
    1.42
     incluyen
    1.40
    includes
    1.34
     incluem
    1.24
    Activations Density 0.055%

    No Known Activations