© 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. 18-GEMMASCOPE-RES-16K
    11. 1638
    Prev
    Next
    INDEX
    Explanations

    phrases expressing difficulty or challenges

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

    "difficult" or its translations

    np_acts-logits-general · gemini-2.0-flash

    difficult to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flames
    -0.63
    __(/*!
    -0.62
     برانيه
    -0.60
     vair
    -0.59
    enumii
    -0.57
    BAU
    -0.55
     onData
    -0.55
    IBOutlet
    -0.55
    이션
    -0.55
    AndEndTag
    -0.54
    POSITIVE LOGITS
    Difficult
    0.85
     Difficult
    0.82
     HARD
    0.80
     Harder
    0.80
     tâche
    0.80
    Dif
    0.78
     difficiles
    0.78
     difficult
    0.77
    difficult
    0.75
     compito
    0.74
    Activations Density 0.091%

    No Known Activations