© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35386
    Prev
    Next
    INDEX
    Explanations

    references to various forms of "utilities" in different contexts

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

    utilities

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    makeText
    -0.48
    posedge
    -0.44
    toThrow
    -0.43
     Aprend
    -0.42
     Embaj
    -0.41
     pieces
    -0.39
    싶
    -0.39
    spec
    -0.38
     Sigism
    -0.37
     albums
    -0.36
    POSITIVE LOGITS
    Utilities
    2.27
     Utilities
    2.02
    utilities
    1.98
     utilities
    1.78
    tilities
    1.03
    ILITIES
    0.93
    electricity
    0.69
     utils
    0.68
    utils
    0.66
    工具类
    0.66
    Activations Density 0.001%

    No Known Activations