© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    keywords that define class structures and their components in programming

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

    Java or code-related "extends"

    np_acts-logits-general · gemini-2.0-flash

    programming language constructs extends

    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
    дії
    -0.44
     da
    -0.43
     resolución
    -0.42
    resolution
    -0.41
    AQ
    -0.41
     resolution
    -0.41
     por
    -0.41
     métallique
    -0.41
     IActionResult
    -0.41
     flat
    -0.40
    POSITIVE LOGITS
     extends
    1.02
    extends
    0.96
     Extend
    0.92
     extending
    0.92
     extend
    0.91
    Personensuche
    0.88
     nakalista
    0.87
    __*/
    0.85
     Extending
    0.84
     Paglinawan
    0.82
    Activations Density 0.098%

    No Known Activations