© 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. 11177
    Prev
    Next
    INDEX
    Explanations

    references to corporate operations and employee involvement

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

    after conjunctions

    np_acts-logits-general · gemini-2.0-flash

    operations and technical terms

    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
     moment
    -0.32
     F
    -0.26
    moment
    -0.26
     popular
    -0.25
    it
    -0.23
    u
    -0.23
    zu
    -0.23
    ↵↵
    -0.22
    ign
    -0.22
    bau
    -0.21
    POSITIVE LOGITS
     ComVisible
    0.86
    contentLoaded
    0.76
     &___
    0.74
    windowFixed
    0.74
     GenerationType
    0.72
     >=",
    0.71
    +#+#
    0.71
     AssemblyTitle
    0.69
    ApplicationTests
    0.69
    WriteTagHelper
    0.68
    Activations Density 0.186%

    No Known Activations