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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8127
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming constructs and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or file paths

    np_acts-logits-general · gemini-2.0-flash

    programming code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.56
     Clegg
    -0.55
     AssemblyCulture
    -0.55
    Personendaten
    -0.52
     OnInit
    -0.51
    kháu
    -0.51
    webElement
    -0.50
    jaardag
    -0.49
     createSlice
    -0.48
    ☸
    -0.47
    POSITIVE LOGITS
    SerializeField
    0.66
    basicConfig
    0.59
    Демографія
    0.55
    Portály
    0.55
    WithIOException
    0.54
    Hochspringen
    0.51
     ArrayAdapter
    0.51
    choline
    0.49
    XMLSchema
    0.48
    ğren
    0.48
    Activations Density 0.109%

    No Known Activations