© 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. 25-GEMMASCOPE-RES-16K
    11. 2045
    Prev
    Next
    INDEX
    Explanations

    documents or phrases related to scientific theories and concepts, particularly in physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.87
     ſtate
    -0.85
     pleaſure
    -0.79
     juſ
    -0.78
     themſelves
    -0.78
     uſe
    -0.76
     deſt
    -0.75
     reaſon
    -0.75
     tranſ
    -0.72
     houſe
    -0.71
    POSITIVE LOGITS
    findpost
    0.63
    oredCriteria
    0.62
     للاسماء
    0.61
     للمعارف
    0.60
    devamını
    0.60
    bootstrapcdn
    0.59
     Taktlose
    0.57
     estekak
    0.57
     middag
    0.56
    sidemargin
    0.56
    Activations Density 1.751%

    No Known Activations