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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4240
    Prev
    Next
    INDEX
    Explanations

    syntax elements and punctuation in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aside
    -0.49
     mêmes
    -0.47
    Besides
    -0.47
    ony
    -0.47
    besides
    -0.46
     apart
    -0.45
     besides
    -0.45
    мимо
    -0.44
    дет
    -0.44
     von
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    1.09
    ChildScrollView
    0.98
     <=",
    0.95
    AndEndTag
    0.95
     ProtoMessage
    0.94
    FieldBuilder
    0.93
    DoubleQuotes
    0.93
    StoryboardSegue
    0.93
    ArrowToggle
    0.92
    IntoConstraints
    0.87
    Activations Density 0.043%

    No Known Activations