© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10153
    Prev
    Next
    INDEX
    Explanations

    references to libraries and functions used in data manipulation and visualization in Python programming

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

    Code, user input, or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    np. followed by a function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.56
    pass
    -0.48
    transQ
    -0.47
     кожу
    -0.46
    patron
    -0.44
    ksesta
    -0.44
     Werth
    -0.43
    ผ่าน
    -0.43
     ante
    -0.43
     Brenner
    -0.43
    POSITIVE LOGITS
     np
    1.89
    np
    1.67
     NP
    0.98
    NP
    0.94
    Np
    0.85
     NPs
    0.71
    NPs
    0.69
     NPCs
    0.65
    numpy
    0.63
     pd
    0.63
    Activations Density 0.117%

    No Known Activations