Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10893
    Prev
    Next
    INDEX
    Explanations

    diverse opening brackets in LaTeX documents

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

    LaTeX document preamble or HTML tags

    np_acts-logits-general · gemini-2.0-flash

    latex document preamble

    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
    횟
    -0.38
     Gefähr
    -0.37
    dolu
    -0.36
     Turquía
    -0.36
     corrupción
    -0.35
     Rejo
    -0.35
    insics
    -0.34
     hoş
    -0.34
    telser
    -0.33
    越好
    -0.33
    POSITIVE LOGITS
    CloseOperation
    0.57
    AnchorStyles
    0.56
     BoxDecoration
    0.56
    IUrlHelper
    0.56
     AssemblyCulture
    0.55
    DeleteBehavior
    0.50
     AssemblyVersion
    0.49
     nahilalakip
    0.49
    RTGC
    0.49
    devServer
    0.48
    Activations Density 0.018%

    No Known Activations