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. 21-GEMMASCOPE-RES-16K
    6. 986
    Prev
    Next
    INDEX
    Explanations

    code-related syntax structures and function definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.54
    ENGTH
    -0.53
    mace
    -0.52
     pulumi
    -0.52
    setLayoutManager
    -0.51
    Cms
    -0.51
     Validators
    -0.50
    MAGIC
    -0.49
     naselje
    -0.48
    DRAFT
    -0.48
    POSITIVE LOGITS
     uLocal
    0.72
     iParam
    0.68
     func
    0.67
    FunctionFlags
    0.67
    func
    0.64
    iLocal
    0.61
     Gleaner
    0.56
     bParam
    0.54
    TemporalType
    0.54
     autorytatywna
    0.52
    Activations Density 0.035%

    No Known Activations