© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8982
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data manipulation and analysis in programming

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

    Code involving dataframes and dates

    np_acts-logits-general · gemini-2.0-flash

    data DataFrame and date operations

    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
    awtextra
    -0.65
     Enix
    -0.59
    AddTagHelper
    -0.56
    httphttps
    -0.56
     StringTokenizer
    -0.54
    +:+
    -0.52
     للمعارف
    -0.52
    findpost
    -0.52
     endian
    -0.48
    ⟬
    -0.47
    POSITIVE LOGITS
     random
    0.41
    tså
    0.40
     hu
    0.37
     date
    0.35
     data
    0.35
     Eichen
    0.33
     table
    0.33
    ToolStripButton
    0.33
     log
    0.33
     secondaires
    0.33
    Activations Density 0.644%

    No Known Activations