© 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. 1477
    Prev
    Next
    INDEX
    Explanations

    concepts and phrases related to practical applications and experiences in various fields

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

    "practical" or "applied" knowledge

    np_acts-logits-general · gemini-2.0-flash

    practical application and solutions

    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
     accidentally
    -0.37
     sinar
    -0.36
     inadvertently
    -0.35
    íso
    -0.34
    новниш
    -0.34
     unintentionally
    -0.33
     normal
    -0.33
     Clements
    -0.32
     slot
    -0.31
     régime
    -0.30
    POSITIVE LOGITS
    practical
    0.98
    Practical
    0.92
     practical
    0.89
     practicality
    0.87
     pragmatic
    0.83
    reality
    0.81
     Practical
    0.80
     praktische
    0.77
     prag
    0.77
     praktischen
    0.77
    Activations Density 0.414%

    No Known Activations