© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6835
    Prev
    Next
    INDEX
    Explanations

    conditional language that indicates possibility or necessity

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

    Following "be" or modal verb

    np_acts-logits-general · gemini-2.0-flash

    possibility, potential, uncertainty

    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
     commandement
    -0.42
    ETHOD
    -0.42
     basically
    -0.39
    XmlIgnore
    -0.37
    gula
    -0.37
     moule
    -0.36
     docteur
    -0.36
    hor
    -0.35
     всегда
    -0.35
    CloseHandle
    -0.35
    POSITIVE LOGITS
    anskje
    0.73
     might
    0.71
     évent
    0.68
     kanskje
    0.68
     måske
    0.67
     möglicherweise
    0.66
     eventuali
    0.63
    อาจ
    0.62
     kanske
    0.61
    might
    0.60
    Activations Density 0.909%

    No Known Activations