Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10287
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "must" indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.93
    Berikut
    -0.70
     Мексичка
    -0.70
     SQLAlchemy
    -0.68
    ברה
    -0.67
     通販
    -0.67
     plana
    -0.65
     infar
    -0.65
     Crowe
    -0.64
    ノリ
    -0.62
    POSITIVE LOGITS
     must
    1.97
    must
    1.85
     Must
    1.84
     MUST
    1.83
    Must
    1.82
    MUST
    1.67
     mustn
    1.35
     muſt
    1.31
     måste
    1.22
     doit
    1.21
    Activations Density 0.058%

    No Known Activations