© 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. 0-GEMMASCOPE-RES-16K
    11. 8361
    Prev
    Next
    INDEX
    Explanations

    the word "meant" and its variations, indicating the significance or implications of statements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſever
    -1.16
     juſ
    -1.12
     fubject
    -1.08
     ―――――
    -1.07
     tranſ
    -1.04
     raiſ
    -1.01
     ſeveral
    -1.00
     ſta
    -1.00
     uſed
    -0.98
     ſub
    -0.96
    POSITIVE LOGITS
     meant
    1.24
     meaning
    1.01
    meant
    0.96
    meaning
    0.85
     Meaning
    0.80
    Meaning
    0.78
     Mean
    0.78
     MEAN
    0.70
     mean
    0.69
     meanings
    0.68
    Activations Density 0.120%

    No Known Activations