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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-GEMMASCOPE-RES-16K
    6. 9494
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that contrast two concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     habet
    -0.58
     étoient
    -0.55
    že
    -0.55
     avoient
    -0.52
     ſmall
    -0.51
    verständlich
    -0.51
     olympique
    -0.50
     fevere
    -0.50
     abrasion
    -0.49
     solidarité
    -0.49
    POSITIVE LOGITS
     raczej
    0.95
     скорее
    0.89
     eher
    0.79
     unknownFields
    0.78
    рее
    0.73
     inkább
    0.71
     חיצוניים
    0.69
    NameInMap
    0.68
    ,:]
    0.68
     rather
    0.67
    Activations Density 0.158%

    No Known Activations