© 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. 8277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or struggle

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

    Preceding the word "difficult"

    np_acts-logits-general · gemini-2.0-flash

    expressing difficulty

    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
    #
    -0.48
    nante
    -0.48
    ControllerAdvice
    -0.46
     MonoBehaviour
    -0.45
     שוליים
    -0.43
    sidemargin
    -0.43
    <?
    -0.43
    částí
    -0.42
    Denn
    -0.41
    zerw
    -0.40
    POSITIVE LOGITS
     difficult
    2.68
     difficulty
    2.58
    difficult
    2.45
     Difficult
    2.40
    Difficult
    2.33
    difficulty
    2.21
     Difficulty
    2.16
     difficile
    2.07
     diffic
    2.07
     difícil
    2.07
    Activations Density 0.470%

    No Known Activations