© 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. 13659
    Prev
    Next
    INDEX
    Explanations

    patterns or sequences involving numbers, particularly in contexts that indicate quantities or measurements

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

    Hexadecimal or numerical sequences

    np_acts-logits-general · gemini-2.0-flash

    anti- prefixes

    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
     Roskov
    -0.57
     Мексичка
    -0.52
    ſelf
    -0.51
    Personensuche
    -0.51
    transQ
    -0.49
    rollment
    -0.48
    fromnode
    -0.46
    RTGC
    -0.45
    RTEE
    -0.44
    
    -0.44
    POSITIVE LOGITS
     Others
    0.38
    ViewImports
    0.37
     plenty
    0.36
     AppCompatTheme
    0.36
     Peer
    0.36
    有沒有
    0.35
    Plenty
    0.35
     Lang
    0.35
     others
    0.35
     Blog
    0.34
    Activations Density 0.721%

    No Known Activations