© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 67
    Prev
    Next
    INDEX
    Explanations

    references to levels of difficulty in games, learning environments, or challenges

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

    task difficulty

    np_acts-logits-general · gemini-2.0-flash

    difficulty levels and challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    onViewCreated
    -0.54
    헌
    -0.53
    kehrt
    -0.46
    ansons
    -0.44
    atzung
    -0.42
    cvt
    -0.41
     mass
    -0.40
    wohn
    -0.40
    ță
    -0.40
     المتحدة
    -0.39
    POSITIVE LOGITS
     difficulty
    2.21
    difficulty
    1.96
     difficult
    1.87
     challenging
    1.86
     Difficulty
    1.85
     Difficult
    1.82
    difficult
    1.79
     Challenging
    1.78
    Difficulty
    1.74
    Difficult
    1.74
    Activations Density 0.227%

    No Known Activations