© 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. 11249
    Prev
    Next
    INDEX
    Explanations

    structured data representations or elements in a programming context

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

    Code snippets with brackets/parentheses

    np_acts-logits-general · gemini-2.0-flash

    programming code delimiters

    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
     the
    -0.48
    icht
    -0.46
    klär
    -0.45
     mə
    -0.45
    océan
    -0.44
     donner
    -0.42
     to
    -0.41
    ranza
    -0.41
    ERTA
    -0.41
    häng
    -0.41
    POSITIVE LOGITS
     متعلقه
    1.19
     للاسماء
    1.09
     esternos
    1.00
     الحره
    0.99
    BeginInit
    0.97
     שוליים
    0.94
     CreateTagHelper
    0.94
    ✨:
    0.94
    ValueStyle
    0.92
    AndEndTag
    0.92
    Activations Density 0.263%

    No Known Activations