© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1398
    Prev
    Next
    INDEX
    Explanations

    various types of factual information and numerical data

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

    Comes after certain nouns

    np_acts-logits-general · gemini-2.0-flash

    quantitative data and specific terminology

    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
     Exacts
    -0.56
    Personendaten
    -0.54
    testens
    -0.51
     Comprometido
    -0.50
    WebVitals
    -0.49
    GEBURTSDATUM
    -0.48
     Jerusalén
    -0.48
    OGND
    -0.47
    HandlerContext
    -0.46
     lenker
    -0.46
    POSITIVE LOGITS
     Un
    0.40
    淡
    0.36
    adaptiveStyles
    0.36
     additional
    0.36
     another
    0.35
     Additional
    0.35
     Vet
    0.34
     U
    0.34
     Hacks
    0.34
    onio
    0.33
    Activations Density 0.722%

    No Known Activations