© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6735
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, especially within the context of interfaces and methods

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

    Preceding letters of .NET interfaces

    np_acts-logits-general · gemini-2.0-flash

    interface prefixes like I or IM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     vôtre
    -0.39
     coû
    -0.36
    SpringBootTest
    -0.36
    ckså
    -0.35
     nôtre
    -0.33
     namely
    -0.32
     while
    -0.32
     itself
    -0.32
     flé
    -0.31
     refroid
    -0.30
    POSITIVE LOGITS
     IERC
    0.84
     Normdatei
    0.70
    ьаж
    0.65
    Ӕ
    0.65
     nakalista
    0.65
    abstractmethod
    0.63
    KURZBESCHREIBUNG
    0.63
     وتسجيلات
    0.63
     Italijanski
    0.62
    /*
    0.62
    Activations Density 0.052%

    No Known Activations