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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3523
    Prev
    Next
    INDEX
    Explanations

    phrases indicating challenges or difficulties

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

    "difficult"

    np_acts-logits-general · gemini-2.0-flash

    describing something difficult

    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
     oprot
    -0.49
     consape
    -0.45
     stazione
    -0.45
    "}},
    -0.43
    Rptr
    -0.43
    protoimpl
    -0.42
     }{@
    -0.42
    astify
    -0.42
     IFTT
    -0.41
     Rivas
    -0.41
    POSITIVE LOGITS
    Difficult
    1.08
     Difficult
    1.05
    difficult
    1.05
     difficult
    0.95
     moeilijk
    0.90
     Hard
    0.89
     diffic
    0.87
    Difficulty
    0.85
     Difficulty
    0.85
     difficile
    0.85
    Activations Density 0.084%

    No Known Activations