© 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. 478
    Prev
    Next
    INDEX
    Explanations

    references to automated scripts and their functionality

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

    Scheduled tasks or automated processes

    np_acts-logits-general · gemini-2.0-flash

    scheduling automated tasks

    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
     imparted
    -0.34
     становника
    -0.30
    herzog
    -0.29
    entierung
    -0.28
    Становништво
    -0.28
     konten
    -0.27
    đen
    -0.27
    derna
    -0.27
    titur
    -0.25
     ráp
    -0.25
    POSITIVE LOGITS
     ویکی‌پدی
    0.80
    WebVitals
    0.64
     automati
    0.64
    UserScript
    0.64
    AsUp
    0.63
    jgl
    0.62
     automating
    0.60
     automático
    0.59
     VIAF
    0.59
     automation
    0.58
    Activations Density 0.338%

    No Known Activations