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. 1553
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation and negative outcomes

    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
     للمعارف
    -0.69
    styleable
    -0.67
    IntoConstraints
    -0.67
    EClass
    -0.63
     poveznice
    -0.61
     Dostupné
    -0.58
    Autoritní
    -0.57
    ReusableCell
    -0.56
    الدراسه
    -0.56
     ListTile
    -0.56
    POSITIVE LOGITS
     caused
    1.56
    caused
    1.48
     causing
    1.33
     Caused
    1.26
     cause
    1.24
    causing
    1.23
     causes
    1.18
     caus
    1.17
     causer
    1.12
     causado
    1.08
    Activations Density 0.311%

    No Known Activations