© 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. 11094
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures related to events and functions

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

    Code or data with special symbols

    np_acts-logits-general · gemini-2.0-flash

    text fields get text

    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
    liesslich
    -0.32
     neumáticos
    -0.29
     sonst
    -0.28
     Grüße
    -0.28
     Grüsse
    -0.27
     obstante
    -0.26
     torno
    -0.26
     ролях
    -0.26
     собі
    -0.26
    richts
    -0.26
    POSITIVE LOGITS
    UnusedPrivate
    0.75
    webElementXpaths
    0.73
    Personendaten
    0.71
    <unused28>
    0.70
    <unused42>
    0.70
    <unused14>
    0.70
    AddTagHelper
    0.70
    bildtitel
    0.70
    <unused79>
    0.70
    <unused1>
    0.69
    Activations Density 0.129%

    No Known Activations