© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and key terms related to particular entities and concepts

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

    followed by names

    np_acts-logits-general · gemini-2.0-flash

    ghost, dog, hero, speed, pointer

    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
    TypedDataSet
    -0.61
     kasarigan
    -0.60
    himovic
    -0.56
     Савезне
    -0.55
    ChildScrollView
    -0.53
     Comprometido
    -0.53
    __':
    -0.53
     Италијани
    -0.53
    WebVitals
    -0.52
    ?>">
    -0.52
    POSITIVE LOGITS
     blog
    0.44
     Blog
    0.41
     Solutions
    0.40
     utafitiHapana
    0.39
     المتحدة
    0.38
     Union
    0.36
     Kass
    0.36
     MDR
    0.35
    Pyx
    0.35
     ویکی‌پدیا
    0.35
    Activations Density 0.504%

    No Known Activations