© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 82649
    Prev
    Next
    INDEX
    Explanations

    phrases related to investment and improvement strategies

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

    invest in, investment pays, foreign countries

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     étoient
    -0.60
     Monfieur
    -0.60
     Winaray
    -0.59
     federally
    -0.58
     Grecian
    -0.57
    WriteTagHelper
    -0.57
     Verſ
    -0.56
     mirth
    -0.54
    thood
    -0.54
    gwin
    -0.54
    POSITIVE LOGITS
     للاسماء
    0.50
    parametrize
    0.38
     obliged
    0.38
     posteriori
    0.38
    hereinafter
    0.37
     disambiguazione
    0.36
    ngOnInit
    0.36
     policemen
    0.36
    ChildScrollView
    0.36
    LoadScene
    0.35
    Activations Density 0.048%

    No Known Activations