© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106138
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and data processing

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

    Function names, method calls, and programming syntax elements in code snippets, particularly focusing on common operations like get/put operations, transaction handling, and API endpoints.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    siąż
    -0.42
     pole
    -0.41
     inserting
    -0.40
    zeera
    -0.40
     getItemId
    -0.39
    Inserting
    -0.38
    httphttps
    -0.38
    verwijspagina
    -0.38
     distinctly
    -0.37
    inser
    -0.36
    POSITIVE LOGITS
     ſta
    0.50
    EndTag
    0.48
    存于互联网档案馆
    0.47
     Reſ
    0.46
    doria
    0.44
    ſelf
    0.44
     verſ
    0.44
     Eſ
    0.43
     juſ
    0.43
     raiſ
    0.42
    Activations Density 0.088%

    No Known Activations