© 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. 10564
    Prev
    Next
    INDEX
    Explanations

    numerical representations or codes, especially in reference to music or programming contexts

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

    Numbers followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    numbers and codes

    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
    الدراسه
    -0.44
    󠁣
    -0.40
    Obrázky
    -0.38
    Derbyniad
    -0.37
     hObject
    -0.37
    EDEFAULT
    -0.36
    ніципа
    -0.35
    iscus
    -0.34
    =?";
    -0.32
     koh
    -0.31
    POSITIVE LOGITS
     initComponents
    0.74
    RegressionTest
    0.66
     <=",
    0.59
     noDo
    0.58
     فريبيس
    0.58
    StoryboardSegue
    0.57
    AutoScale
    0.57
    ItemBackground
    0.55
     nonUne
    0.54
    IVEREF
    0.52
    Activations Density 0.490%

    No Known Activations